© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35558
    Prev
    Next
    INDEX
    Explanations

    code blocks with try/except

    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_7_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
    c
    0.50
    te
    0.49
    w
    0.46
    i
    0.46
    "
    0.45
    ي
    0.45
    f
    0.44
    k
    0.43
    v
    0.42
    in
    0.41
    POSITIVE LOGITS
    褰
    0.35
     असून
    0.34
    ের
    0.34
     ,
    0.33
    均
    0.32
    的地
    0.32
    ),
    0.31
     použ
    0.31
     Orche
    0.30
     Slovenia
    0.29
    Activations Density 0.002%

    No Known Activations