© 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. 111684
    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
    in
    1.58
    .
    1.48
    u
    1.40
    ip
    1.29
    ac
    1.26
    '
    1.26
    1
    1.20
    he
    1.19
    an
    1.14
    ze
    1.13
    POSITIVE LOGITS
    د
    1.35
    ט
    1.07
    д
    1.04
    ле
    0.93
    دق
    0.93
    З
    0.92
    دود
    0.91
    دع
    0.91
    리로
    0.91
    ש
    0.91
    Activations Density 0.000%

    No Known Activations