© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196356
    Prev
    Next
    INDEX
    Explanations

    ageless, -ism, -ist, -ged

    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_4_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
    ны
    1.02
    ла
    0.94
    '
    0.87
    0.86
     Gletscher
    0.84
    lished
    0.83
    ца
    0.83
    не
    0.82
    ле
    0.79
    лно
    0.78
    POSITIVE LOGITS
    ur
    0.97
    i
    0.97
    in
    0.96
    ä
    0.95
    ter
    0.91
    I
    0.86
    d
    0.83
    er
    0.82
    s
    0.82
     with
    0.81
    Activations Density 0.001%

    No Known Activations