© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104636
    Prev
    Next
    INDEX
    Explanations

    virtual, Pauschbetrag, PaulsLey

    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_1_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
    i
    1.76
    u
    1.73
    en
    1.70
    ي
    1.60
    on
    1.57
    。
    1.54
    il
    1.52
    o
    1.52
    ing
    1.47
    re
    1.44
    POSITIVE LOGITS
    お金
    1.19
    ある
    1.08
    危害
    1.02
     are
    1.01
     खोज
    1.01
     It
    1.00
    很多的
    1.00
    取り付け
    0.99
    很多
    0.95
    apping
    0.94
    Activations Density 0.000%

    No Known Activations