© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136471
    Prev
    Next
    INDEX
    Explanations

    是由 / is from

    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_12_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
    \&
    0.54
    rosion
    0.54
    醤
    0.52
    design
    0.51
    െന്ന്
    0.50
    おしゃれ
    0.50
     목록
    0.49
    9
    0.49
     Name
    0.49
     প্রক্রিয়াধীন
    0.48
    POSITIVE LOGITS
    νά
    0.50
    ко
    0.50
    шего
    0.49
     verdadero
    0.49
    виа
    0.49
     ?)
    0.48
    ком
    0.48
    ких
    0.48
    वेल
    0.48
     youths
    0.48
    Activations Density 0.000%

    No Known Activations