© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51170
    Prev
    Next
    INDEX
    Explanations

    NRPROV

    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_10_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
     bevor
    0.79
     bringt
    0.75
     lässt
    0.74
     you
    0.72
    вро
    0.71
    <unused2221>
    0.70
     großer
    0.70
    larını
    0.69
     stabil
    0.67
    :}
    0.67
    POSITIVE LOGITS
    and
    0.82
    ações
    0.82
    es
    0.76
    ip
    0.73
    は
    0.71
    는
    0.70
    ação
    0.70
    ست
    0.69
    izaciones
    0.68
    マ
    0.68
    Activations Density 0.021%

    No Known Activations