© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65194
    Prev
    Next
    INDEX
    Explanations

    explore Shinjuku

    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_41_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
     MRC
    0.40
    mış
    0.37
    ┕
    0.36
    IDTH
    0.34
     pullback
    0.34
    딴
    0.34
    akang
    0.34
    摄
    0.34
     Mushroom
    0.33
    дца
    0.33
    POSITIVE LOGITS
     Per
    0.71
    Eva
    0.63
    Per
    0.62
     Ev
    0.62
    Ev
    0.61
     Eva
    0.61
    per
    0.52
     Duarte
    0.48
     év
    0.45
     per
    0.45
    Activations Density 0.003%

    No Known Activations