© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103520
    Prev
    Next
    INDEX
    Explanations

    Corea, design, stories, before

    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_1_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
    ود
    1.42
    وم
    1.36
    ک
    1.36
    ون
    1.18
    ut
    1.12
    ی
    1.12
    c
    1.11
    は
    1.10
    는
    1.08
    ل
    1.07
    POSITIVE LOGITS
    <0x80>
    1.74
    ;
    1.68
    ?
    1.37
    :
    1.32
    -
    1.30
    _
    1.28
    ),
    1.27
    '
    1.13
    /
    1.10
    ิ
    1.04
    Activations Density 0.000%

    No Known Activations