© 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. 91503
    Prev
    Next
    INDEX
    Explanations

    par=google

    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
    д
    0.77
    린
    0.77
    ם
    0.74
    맇
    0.73
    စျေး
    0.72
    ل
    0.70
    नान
    0.70
    ма
    0.69
    recursive
    0.69
    ה
    0.69
    POSITIVE LOGITS
    (
    0.77
    <0x94>
    0.66
     l
    0.63
    "
    0.61
     be
    0.60
    <
    0.59
    '
    0.58
     beve
    0.57
     I
    0.57
    <0x8C>
    0.56
    Activations Density 0.001%

    No Known Activations