© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162150
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
     be
    1.20
    h
    1.00
    AL
    0.99
    エ
    0.96
     as
    0.94
    <0x8D>
    0.93
    AR
    0.92
    <0xBB>
    0.91
    RA
    0.90
    ";
    0.88
    POSITIVE LOGITS
    ون
    1.44
    ي
    1.33
    ل
    1.23
    ux
    1.21
    it
    1.18
    т
    1.18
    ב
    1.15
    ات
    1.14
    مع
    1.14
    يد
    1.11
    Activations Density 0.000%

    No Known Activations