© 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. 9133
    Prev
    Next
    INDEX
    Explanations

    mentions of turning something on or off

    oai_token-act-pair · gemini-2.0-flash

    technical functionality and commands

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

    turn

    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
    
    -0.70
    parsedMessage
    -0.65
     esternos
    -0.61
     turn
    -0.59
    Turn
    -0.57
     виправивши
    -0.56
    turn
    -0.56
     ujednoznacz
    -0.56
     turns
    -0.55
    turned
    -0.55
    POSITIVE LOGITS
    cinia
    0.53
    varu
    0.51
    orcid
    0.50
    LIA
    0.48
     antworte
    0.48
    tovers
    0.48
     оригіналу
    0.48
    abank
    0.47
    alisis
    0.47
     sobres
    0.46
    Activations Density 3.074%

    No Known Activations