© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35413
    Prev
    Next
    INDEX
    Explanations

    until followed by a pronoun or article

    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_7_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
    for
    0.65
     a
    0.64
    jats
    0.63
    l
    0.63
    k
    0.61
    <0x80>
    0.60
     दोन
    0.60
    ig
    0.59
    ir
    0.59
    after
    0.59
    POSITIVE LOGITS
    ۔
    0.93
    は
    0.92
     in
    0.89
    는
    0.86
    с
    0.82
    ।
    0.81
    ።
    0.76
    มัน
    0.74
     are
    0.70
    س
    0.70
    Activations Density 0.000%

    No Known Activations