© 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. 86140
    Prev
    Next
    INDEX
    Explanations

    walking, watching, wars, github, building, neutral

    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
    다
    0.78
    கே
    0.73
    niji
    0.72
    ন
    0.72
    in
    0.68
    ）,
    0.67
    は
    0.67
     Είναι
    0.64
    geben
    0.63
    دیا
    0.62
    POSITIVE LOGITS
    t
    0.88
    ä
    0.77
    wl
    0.73
    up
    0.73
    tR
    0.71
    itt
    0.71
    ag
    0.70
    tap
    0.68
    ture
    0.66
    v
    0.66
    Activations Density 0.008%

    No Known Activations