© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209354
    Prev
    Next
    INDEX
    Explanations

    potential of

    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_20_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
    潅
    0.41
    ቨ
    0.40
     sérieux
    0.40
    hauses
    0.38
     vals
    0.38
    putString
    0.37
     trazendo
    0.35
    žių
    0.35
    椒
    0.35
    спекти
    0.35
    POSITIVE LOGITS
    CRM
    0.39
    back
    0.39
    ISAM
    0.39
    তাহার
    0.38
     terminated
    0.38
    COM
    0.38
    ／
    0.38
    loin
    0.36
    aging
    0.36
    SHOP
    0.36
    Activations Density 0.004%

    No Known Activations