© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161107
    Prev
    Next
    INDEX
    Explanations

    homey, rustic, old-timey flavor

    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_2_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
    这
    1.12
    را
    1.10
    他
    1.04
    社会
    1.03
     وأ
    1.03
     hran
    1.02
     pravo
    1.02
     seizoen
    0.99
    ╅
    0.99
     luglio
    0.98
    POSITIVE LOGITS
    0
    1.94
    .
    1.69
    v
    1.65
    as
    1.63
    on
    1.58
    at
    1.53
    os
    1.53
    1
    1.44
    s
    1.40
    ee
    1.31
    Activations Density 0.000%

    No Known Activations