© 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. 158026
    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
    াতি
    1.05
    ות
    1.02
     fenders
    1.02
     mantras
    0.93
    Ს
    0.92
     as
    0.91
    ೇತ್ರ
    0.90
     prohibitions
    0.89
    ין
    0.89
     revistas
    0.89
    POSITIVE LOGITS
    1.38
    .
    1.27
    p
    1.20
    -
    1.17
    c
    1.16
    ä
    1.14
    ก
    1.13
    og
    1.02
    r
    1.02
    m
    1.00
    Activations Density 0.000%

    No Known Activations