© 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. 209835
    Prev
    Next
    INDEX
    Explanations

    .info text

    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
    es
    0.74
    ang
    0.69
    p
    0.68
    é
    0.66
    ep
    0.66
     freezing
    0.66
    ed
    0.64
    érm
    0.64
    ad
    0.63
     hurtful
    0.63
    POSITIVE LOGITS
    ک
    0.92
    ۹
    0.75
    ل
    0.71
    för
    0.68
    ክት
    0.68
    󠁧
    0.66
    )).
    0.65
    نو
    0.64
    $),
    0.63
    ح
    0.63
    Activations Density 0.001%

    No Known Activations