© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160369
    Prev
    Next
    INDEX
    Explanations

    COV, vault, video, ão

    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
     to
    1.60
     as
    1.11
    '
    1.08
    to
    0.99
    ppure
    0.91
    '$\
    0.90
    1
    0.89
    ش
    0.89
     malas
    0.88
     parro
    0.88
    POSITIVE LOGITS
    t
    1.09
    }"
    1.03
    ।
    1.00
    IE
    0.96
    もら
    0.95
    in
    0.95
    }$.
    0.94
    ،
    0.93
    も
    0.91
    ALE
    0.90
    Activations Density 0.000%

    No Known Activations