© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 26945
    Prev
    Next
    INDEX
    Explanations

    game titles and genres

    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_10_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
    leşt
    0.39
    <unused1038>
    0.38
    𝙙
    0.37
    𝙢
    0.36
    füh
    0.36
    г
    0.36
     đội
    0.35
    bouw
    0.35
    ostics
    0.34
    mö
    0.34
    POSITIVE LOGITS
    Time
    0.40
    くり
    0.40
    Stop
    0.40
    Service
    0.40
    {
    0.40
    '),
    0.39
    した
    0.39
    1
    0.38
    Class
    0.37
    PL
    0.37
    Activations Density 0.046%

    No Known Activations