© 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. 38050
    Prev
    Next
    INDEX
    Explanations

    is followed by specific continuations

    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
    ע
    0.77
     can
    0.75
    로
    0.73
    ج
    0.72
    ;
    0.65
    ص
    0.63
    その
    0.63
    c
    0.63
     rencana
    0.61
    ?
    0.61
    POSITIVE LOGITS
    that
    0.82
    I
    0.79
    ర్
    0.73
    า
    0.72
    ры
    0.65
    ла
    0.64
    ة
    0.64
    ែ
    0.64
    role
    0.61
    B
    0.60
    Activations Density 0.004%

    No Known Activations