© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 203398
    Prev
    Next
    INDEX
    Explanations

    socialist

    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
     a
    1.16
    {
    1.16
    (
    1.07
    RAFT
    1.05
    $\
    0.99
    $
    0.99
    5
    0.98
    $.
    0.95
    ।
    0.95
    ?
    0.91
    POSITIVE LOGITS
    s
    1.27
    ی
    1.09
    는
    1.00
    </h6>
    0.98
    ্জ
    0.92
    sning
    0.92
    تق
    0.91
    με
    0.90
    ب
    0.89
    是
    0.89
    Activations Density 0.000%

    No Known Activations