© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13965
    Prev
    Next
    INDEX
    Explanations

    the slavic languages croatian and slovak, as well as abbreviations for football clubs

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    homonymie
    -0.77
    rungsseite
    -0.61
    TestingModule
    -0.58
    sidemargin
    -0.58
     كومونز
    -0.57
    AnimationsModule
    -0.57
    ValueStyle
    -0.56
     سكانية
    -0.55
    InitVars
    -0.55
    مراجع
    -0.54
    POSITIVE LOGITS
     papy
    0.61
     Indoch
    0.59
     lapsed
    0.55
    ########.
    0.51
     démo
    0.51
     Bona
    0.51
     himo
    0.50
    Diweddarwch
    0.49
     ladder
    0.49
     Snowy
    0.49
    Activations Density 0.166%

    No Known Activations