© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11383
    Prev
    Next
    INDEX
    Explanations

    intelligence community assessments

    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_13_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
     (
    0.51
     [
    0.50
     verbal
    0.44
     Defense
    0.43
     Montana
    0.42
    ствии
    0.42
    нович
    0.42
     Prom
    0.42
     bench
    0.42
     finger
    0.42
    POSITIVE LOGITS
    There
    0.50
    Item
    0.49
    Shakespeare
    0.48
     zmiany
    0.48
    Mul
    0.47
    埋
    0.47
    スマホ
    0.47
    លោក
    0.45
    Those
    0.45
    MUL
    0.45
    Activations Density 0.000%

    No Known Activations