© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121089
    Prev
    Next
    INDEX
    Explanations

    UI elements and data handling

    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_27_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
     उल्लेखनीय
    0.39
    potent
    0.37
    Пре
    0.36
    Defendant
    0.36
    ສະ
    0.36
    display
    0.36
    ^{*}+
    0.35
    当作
    0.35
     నేపథ్యంలో
    0.35
    新たに
    0.35
    POSITIVE LOGITS
     numOf
    0.40
    人們
    0.38
     varient
    0.38
     entreprises
    0.38
     strips
    0.37
    ország
    0.37
     людям
    0.37
    影视
    0.37
     mye
    0.36
     biti
    0.36
    Activations Density 0.000%

    No Known Activations