© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260972
    Prev
    Next
    INDEX
    Explanations

    be verbs like becoming, beating

    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_5_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
     to
    1.55
     not
    1.05
    haven
    0.98
    amı
    0.96
    IS
    0.90
    ので
    0.89
    $.)
    0.89
    >
    0.89
     সূত্র
    0.88
     at
    0.88
    POSITIVE LOGITS
    ك
    2.09
    ת
    1.51
    ت
    1.43
    고
    1.37
    ता
    1.36
    c
    1.31
    т
    1.23
    k
    1.21
    X
    1.20
    들이
    1.19
    Activations Density 0.007%

    No Known Activations