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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205028
    Prev
    Next
    INDEX
    Explanations

    you know, you said

    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_37_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
    格式
    0.37
     እንደ
    0.37
     ಸ್ವಲ್ಪ
    0.36
     الخامسه
    0.35
    ্ের
    0.35
     evin
    0.35
     отдельно
    0.35
    ྔ
    0.35
    ிறது
    0.34
    SRPC
    0.33
    POSITIVE LOGITS
    घन
    0.39
    list
    0.38
    box
    0.38
     İşte
    0.38
    lista
    0.37
    Gh
    0.37
    Hundred
    0.37
     Cultura
    0.36
    pointA
    0.36
     Meet
    0.36
    Activations Density 0.001%

    No Known Activations