© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14453
    Prev
    Next
    INDEX
    Explanations

    text discussing lights or LEDs that indicate when something is on or in use, or the potential privacy concerns surrounding those lights.

    oai_token-act-pair · gemini-2.0-flash

    actions related to turning on or switching devices

    np_token-act-pair-logits · gpt-4o-mini

    Turning on or off

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.70
    webElementXpaths
    -0.49
    zionalità
    -0.48
     quirúrg
    -0.47
    /*
    -0.46
     trasera
    -0.45
    зулта
    -0.45
    |}{$
    -0.45
    }[!
    -0.45
     صالح
    -0.44
    POSITIVE LOGITS
     switched
    0.75
     switch
    0.74
     turns
    0.73
     turn
    0.70
     switching
    0.70
     turning
    0.69
    Turned
    0.67
     Turn
    0.66
     turned
    0.66
     Fired
    0.65
    Activations Density 2.660%

    No Known Activations