© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85824
    Prev
    Next
    INDEX
    Explanations

    job id or type designation

    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_3_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
    ي
    0.74
    ה
    0.72
     sceGu
    0.71
     različ
    0.66
    맇
    0.65
    。",
    0.64
    ",[(
    0.64
    િવસ
    0.63
    ９
    0.63
    Პ
    0.63
    POSITIVE LOGITS
    -
    0.78
    te
    0.77
    .
    0.75
    ir
    0.74
    I
    0.71
    '
    0.69
     I
    0.65
    ma
    0.65
    ap
    0.63
    >
    0.61
    Activations Density 0.004%

    No Known Activations