© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10490
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "wide" and sometimes other words when near "wide"

    oai_token-act-pair · gemini-2.0-flash

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     en
    -0.65
     o
    -0.65
    .
    -0.63
     :
    -0.60
     -
    -0.60
     de
    -0.57
     .
    -0.56
     mit
    -0.56
    ta
    -0.55
    POSITIVE LOGITS
     myſelf
    1.37
     Efq
    1.32
     ſeveral
    1.28
     chofe
    1.26
     Monfieur
    1.24
     Anſ
    1.20
     whoſe
    1.19
    ſelves
    1.18
     uſed
    1.18
    AccessorTable
    1.17
    Activations Density 1.181%

    No Known Activations