© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146140
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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_59_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
    ICSS
    0.44
    𠃍
    0.42
    cales
    0.39
    CPC
    0.38
     takut
    0.37
    Ys
    0.36
     Roe
    0.36
    至於
    0.36
     Rabbi
    0.36
    Israeli
    0.35
    POSITIVE LOGITS
     wire
    1.00
    wire
    0.99
     Wire
    0.96
     (
    0.88
    Wire
    0.87
     wires
    0.86
     WIRE
    0.78
    Wires
    0.77
    wires
    0.75
    wiring
    0.67
    Activations Density 0.001%

    No Known Activations