© 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. 14609
    Prev
    Next
    INDEX
    Explanations

    questions, requests, or offers of advice

    oai_token-act-pair · gemini-2.0-flash

    any

    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
    UnsafeEnabled
    -0.76
    webElementXpaths
    -0.76
    AutoField
    -0.66
     ModelExpression
    -0.65
    RTLD
    -0.60
     كومونز
    -0.60
    NameInMap
    -0.57
     mergeFrom
    -0.56
     unknownFields
    -0.56
    ConstraintMaker
    -0.56
    POSITIVE LOGITS
     contextLoads
    0.70
    addPreferredGap
    0.59
    Beijinhos
    0.55
    Obrigada
    0.52
    汰
    0.52
     Feedback
    0.51
    "]);
    0.50
     experimentally
    0.50
     getArguments
    0.50
     modelling
    0.48
    Activations Density 8.220%

    No Known Activations