© 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. 231596
    Prev
    Next
    INDEX
    Explanations

    doujin annotation

    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
    ight
    1.11
    </h2>
    0.98
     り
    0.88
     USAF
    0.84
    <unused43>
    0.82
     사람
    0.82
     کیا
    0.81
     наші
    0.79
    ot
    0.78
    <0x0D>
    0.77
    POSITIVE LOGITS
    ת
    1.41
    ية
    1.30
    s
    1.25
    ي
    1.24
    ك
    1.17
    י
    1.13
    ।
    1.13
    {
    1.10
    as
    1.09
    ות
    1.07
    Activations Density 0.000%

    No Known Activations