© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5871
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     ),
    0.37
     }{}_{\
    0.36
     substitutes
    0.36
    ୱ
    0.34
    $$_
    0.34
     後
    0.34
    жением
    0.34
     صغير
    0.34
     जान
    0.34
     $_{\
    0.34
    POSITIVE LOGITS
    strup
    0.39
    steak
    0.39
     Guth
    0.38
    лур
    0.38
    load
    0.37
    auf
    0.37
     Hugh
    0.37
    AutoComplete
    0.37
    aught
    0.36
    对象
    0.36
    Activations Density 0.001%

    No Known Activations