© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87486
    Prev
    Next
    INDEX
    Explanations

    leggy

    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
     tienen
    0.74
     will
    0.66
     betrachtet
    0.65
    ي
    0.64
     хочет
    0.60
     entfernt
    0.58
     hace
    0.58
     terug
    0.57
     verwendet
    0.57
     decât
    0.57
    POSITIVE LOGITS
    t
    0.84
    _
    0.75
    lake
    0.73
    lions
    0.71
    h
    0.71
    یاء
    0.70
    یک
    0.68
    یکه
    0.66
    liku
    0.66
    лох
    0.66
    Activations Density 0.000%

    No Known Activations