© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88680
    Prev
    Next
    INDEX
    Explanations

    code comments and read/write operations

    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_18_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
    of
    0.56
    '
    0.54
    o
    0.51
     with
    0.47
     של
    0.47
    $
    0.47
     dangerously
    0.46
    กระ
    0.46
     of
    0.46
     partnership
    0.46
    POSITIVE LOGITS
     Maugin
    0.59
    ুগত্য
    0.54
     individui
    0.54
    ꞎ
    0.53
     Individuals
    0.52
    йдз
    0.52
    Ⲑ
    0.52
     indivíduos
    0.50
     Exploration
    0.50
    tschaft
    0.50
    Activations Density 0.000%

    No Known Activations