© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199164
    Prev
    Next
    INDEX
    Explanations

    polymorphs, Icahn, diet

    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_9_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
     enhances
    0.61
     Enh
    0.59
    䔉
    0.58
     algebra
    0.52
     excuses
    0.52
     enhancers
    0.52
     improves
    0.50
     abd
    0.50
    insuff
    0.50
     income
    0.50
    POSITIVE LOGITS
    ୨
    0.45
    м
    0.44
    రు
    0.44
    release
    0.42
    fmt
    0.40
     той
    0.39
    refour
    0.39
    비를
    0.39
     ਨੂੰ
    0.39
    튜
    0.39
    Activations Density 0.000%

    No Known Activations