© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196401
    Prev
    Next
    INDEX
    Explanations

    of whom

    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_9_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
    ك
    0.34
    on
    0.33
    지
    0.31
    g
    0.29
    as
    0.28
    n
    0.28
    u
    0.27
    ת
    0.27
    માં
    0.27
    y
    0.26
    POSITIVE LOGITS
     comedians
    0.35
     problemi
    0.30
    ۹
    0.29
     पोर्न
    0.29
     километ
    0.29
     kawaii
    0.28
     phonon
    0.28
     headlight
    0.28
     personaggi
    0.28
     guitarist
    0.27
    Activations Density 0.003%

    No Known Activations