© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3993
    Prev
    Next
    INDEX
    Explanations

    Swift code syntax, particularly around optional variables, function definitions, and control flow

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للاسماء
    -1.30
     للمعارف
    -1.12
    ThroughAttribute
    -1.09
    ValueStyle
    -1.00
    Gambas
    -0.94
    Personensuche
    -0.93
     متعلقه
    -0.92
     فريبيس
    -0.89
    UserScript
    -0.89
     Theſe
    -0.88
    POSITIVE LOGITS
     Let
    0.49
     
    0.49
     M
    0.48
     Sim
    0.47
     Mon
    0.46
     E
    0.45
     Down
    0.43
     Object
    0.43
     My
    0.43
     Le
    0.43
    Activations Density 1.608%

    No Known Activations