© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35277
    Prev
    Next
    INDEX
    Explanations

    section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    absch
    0.38
    mtrl
    0.32
    rought
    0.32
     compless
    0.32
    砟
    0.32
    ability
    0.31
    ンス
    0.31
    nable
    0.31
    ,}
    0.31
    achev
    0.31
    POSITIVE LOGITS
    :
    0.89
    ：
    0.81
     :
    0.68
    ៖
    0.63
     –
    0.61
     ：
    0.55
     -
    0.53
    ：「
    0.53
    ：《
    0.52
    ::
    0.50
    Activations Density 0.296%

    No Known Activations