© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205368
    Prev
    Next
    INDEX
    Explanations

    dates

    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_6_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
    B
    1.26
    H
    1.19
    C
    1.16
    R
    1.16
    X
    1.13
    Α
    1.13
    P
    1.12
    Đ
    1.11
    L
    1.09
    Z
    1.09
    POSITIVE LOGITS
    in
    1.46
    os
    1.43
    ia
    1.34
    é
    1.34
    á
    1.31
    ik
    1.28
    ut
    1.21
    ма
    1.20
    er
    1.19
    at
    1.19
    Activations Density 0.000%

    No Known Activations