© 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. 6133
    Prev
    Next
    INDEX
    Explanations

    code-related tokens that are often found near parenthesis or comparison and assignment operators like =

    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
     betweenstory
    -0.97
     Efq
    -0.94
     itſelf
    -0.92
     ſeveral
    -0.91
    LookAnd
    -0.91
     Theſe
    -0.90
    Personendaten
    -0.89
     Monfieur
    -0.88
     Reſ
    -0.87
     Majefty
    -0.86
    POSITIVE LOGITS
     (
    0.75
     ()
    0.66
     
    0.59
     ($
    0.51
     it
    0.50
     ev
    0.47
     sal
    0.46
     $(
    0.45
     X
    0.45
     anti
    0.45
    Activations Density 3.585%

    No Known Activations