© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210656
    Prev
    Next
    INDEX
    Explanations

    responsive

    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_5_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
    s
    1.65
    2
    1.56
    b
    1.53
    ll
    1.35
    8
    1.34
    la
    1.30
    d
    1.29
    w
    1.29
    3
    1.28
    li
    1.26
    POSITIVE LOGITS
     в
    0.95
     товар
    0.94
    ecek
    0.94
    ент
    0.93
    itoare
    0.93
    ́u
    0.91
     can
    0.90
    ệt
    0.88
     contemplative
    0.88
    ције
    0.87
    Activations Density 0.000%

    No Known Activations