© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143884
    Prev
    Next
    INDEX
    Explanations

    states, bytes, cytochrome, Bread, like, bail, swift, moving

    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_0_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
     vaikka
    0.55
     помещение
    0.51
    ทีม
    0.50
    ཝ
    0.49
    DU
    0.49
    GE
    0.48
    Kap
    0.48
    ME
    0.48
    ൭
    0.48
    Au
    0.47
    POSITIVE LOGITS
    c
    0.66
    un
    0.56
    ata
    0.52
    ir
    0.51
    cement
    0.51
    d
    0.51
    scalars
    0.50
    ob
    0.49
    dal
    0.48
    rals
    0.48
    Activations Density 0.000%

    No Known Activations