© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127042
    Prev
    Next
    INDEX
    Explanations

    `w/y` format, double vanity

    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_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
    in
    0.89
    I
    0.88
    ,
    0.79
    com
    0.77
    et
    0.77
    an
    0.76
    B
    0.73
    Group
    0.69
    j
    0.68
    SH
    0.66
    POSITIVE LOGITS
    ่า
    0.84
    тна
    0.71
    <tr>
    0.67
     dáng
    0.63
    ینا
    0.63
    ियस
    0.62
     mancanza
    0.62
    bindingFields
    0.61
     remastered
    0.61
    atura
    0.61
    Activations Density 0.003%

    No Known Activations