© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196033
    Prev
    Next
    INDEX
    Explanations

    topic modeling

    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_4_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
    ରି
    0.56
    行情
    0.52
    hlen
    0.51
     лише
    0.51
    ;
    0.50
    ressive
    0.50
     förm
    0.49
    hko
    0.48
    ota
    0.47
    ไม่
    0.47
    POSITIVE LOGITS
    of
    0.71
    يل
    0.70
    াস
    0.67
    ции
    0.65
    ח
    0.64
    기를
    0.63
     školy
    0.63
    াল
    0.62
    ית
    0.62
     Investigación
    0.61
    Activations Density 0.000%

    No Known Activations