© 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. 126648
    Prev
    Next
    INDEX
    Explanations

    lanolin

    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
    ו
    0.82
    ن
    0.73
    ার
    0.72
    ه
    0.70
    و
    0.68
     The
    0.66
    cot
    0.65
    z
    0.64
    ो
    0.64
    0
    0.63
    POSITIVE LOGITS
    ).
    0.66
     be
    0.64
    (
    0.59
     restrained
    0.56
    itt
    0.55
    ।
    0.55
     can
    0.55
    agoza
    0.55
    OUBLE
    0.54
    로
    0.53
    Activations Density 0.000%

    No Known Activations