© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2913
    Prev
    Next
    INDEX
    Explanations

    ratio 1:x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ことが
    0.36
     contrat
    0.34
    서
    0.33
    ारा
    0.31
     మాత్ర
    0.31
    rechte
    0.31
     besar
    0.31
    ن
    0.31
     conocer
    0.30
    パンツ
    0.30
    POSITIVE LOGITS
    faced
    0.35
    д
    0.35
    asche
    0.32
     objectMapper
    0.32
    ře
    0.32
    fli
    0.31
    ת
    0.31
     VARCHAR
    0.31
    django
    0.31
    ০
    0.30
    Activations Density 0.019%

    No Known Activations