© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13220
    Prev
    Next
    INDEX
    Explanations

    declarative base

    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_13_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
    u
    0.35
     are
    0.32
    графи
    0.30
     can
    0.29
    can
    0.29
     pouvez
    0.29
    anlage
    0.29
     качественно
    0.29
    স্থান
    0.29
    </code>
    0.28
    POSITIVE LOGITS
     Bison
    0.35
     संघर्ष
    0.33
     AFB
    0.31
     Huddersfield
    0.31
     सीजन
    0.30
     뉴
    0.30
     Burlington
    0.30
    Хар
    0.30
     Instead
    0.30
     للح
    0.30
    Activations Density 0.008%

    No Known Activations