© 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. 137505
    Prev
    Next
    INDEX
    Explanations

    don't move a muscle

    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
    没有任何
    0.66
    nothing
    0.57
    這一
    0.55
    不可以
    0.54
    beweg
    0.54
    蕲
    0.54
     atthakath
    0.53
     没有
    0.52
    sna
    0.52
     İli
    0.52
    POSITIVE LOGITS
    ИН
    0.63
    ו
    0.59
     д
    0.57
     ITS
    0.57
     o
    0.56
     В
    0.55
    И
    0.55
     TAS
    0.54
     CORE
    0.54
     CASES
    0.54
    Activations Density 0.000%

    No Known Activations