© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42901
    Prev
    Next
    INDEX
    Explanations

    time, chunks, library, vector, happier, you, wait, values

    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_22_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
     ไ
    0.51
     none
    0.45
     हानि
    0.44
     없음
    0.43
     τα
    0.42
     Executor
    0.42
     бело
    0.41
     desolate
    0.40
     NONE
    0.40
    邙
    0.40
    POSITIVE LOGITS
    upa
    0.39
    しているので
    0.39
    Islam
    0.37
    ইসলাম
    0.37
    вича
    0.37
     immunological
    0.36
     اسلام
    0.36
    تش
    0.36
     اسلامی
    0.36
    ப்பினர்
    0.36
    Activations Density 0.000%

    No Known Activations