© 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. 107827
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ب
    1.39
    ك
    1.29
    L
    1.28
    M
    1.26
    P
    1.25
    R
    1.20
    H
    1.16
    ج
    1.16
    C
    1.16
    N
    1.15
    POSITIVE LOGITS
     and
    1.20
    are
    1.09
    こと
    1.03
    é
    1.00
     on
    0.98
    +
    0.98
    ado
    0.97
    atio
    0.95
     with
    0.93
    েন
    0.93
    Activations Density 0.000%

    No Known Activations