© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53809
    Prev
    Next
    INDEX
    Explanations

    and

    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_55_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
    ப்புக
    0.35
     ශ
    0.34
    owania
    0.34
    oe
    0.33
    यंस
    0.33
    )^{*}
    0.33
    ushal
    0.33
    awie
    0.32
    uminate
    0.32
    =\$
    0.32
    POSITIVE LOGITS
     特に
    0.40
     脚
    0.39
     głównie
    0.38
     добра
    0.37
     đến
    0.37
    Thermal
    0.35
     当然
    0.35
     κυ
    0.35
     Piece
    0.35
     rozm
    0.35
    Activations Density 0.001%

    No Known Activations