© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130960
    Prev
    Next
    INDEX
    Explanations

    Alanis, Alaina, Alisa, Wales

    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
    <0x80>
    1.39
    {
    1.18
    ),
    1.12
    )";
    1.12
     I
    1.06
    ;
    1.06
    ).}
    1.05
    0
    1.04
    I
    1.03
    ０
    1.02
    POSITIVE LOGITS
    os
    1.28
    as
    1.23
    ной
    1.21
    on
    1.11
    durch
    1.09
    r
    1.07
    ul
    1.06
    مة
    1.05
    mäßig
    1.03
    osť
    1.02
    Activations Density 0.000%

    No Known Activations