© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8010
    Prev
    Next
    INDEX
    Explanations

    date and update information

    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_3_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
    א
    2.77
    bark
    2.63
    м
    2.51
     ramping
    2.47
    ServletContext
    2.45
    जब
    2.37
    findOrFail
    2.37
     licenci
    2.30
     sparsely
    2.26
    ー
    2.26
    POSITIVE LOGITS
    namento
    2.63
    ب
    2.61
    gies
    2.53
    versammlung
    2.53
    و
    2.50
     сто
    2.50
    शील
    2.46
     кап
    2.44
    આ
    2.42
     алкого
    2.38
    Activations Density 0.062%

    No Known Activations