© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16153
    Prev
    Next
    INDEX
    Explanations

    many different topical words and phrases, but specifically those that are about something completed and also frozen desserts.

    oai_token-act-pair · gemini-2.0-flash

    informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     läßt
    -0.78
     muß
    -0.74
     mußte
    -0.68
     daß
    -0.68
     (;;)
    -0.66
     Moslem
    -0.64
     mußten
    -0.63
     müßte
    -0.62
     vícti
    -0.60
     "'");
    -0.58
    POSITIVE LOGITS
     impactful
    0.76
    TLDR
    0.69
    ± 
    0.69
    Lastly
    0.69
     overarching
    0.67
     incentiv
    0.67
     leveraging
    0.66
     nuanced
    0.66
     timelines
    0.65
     — 
    0.65
    Activations Density 8.189%

    No Known Activations