© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45252
    Prev
    Next
    INDEX
    Explanations

    *adjusts, bats, tail, looks

    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_13_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
    Б
    0.56
    Ба
    0.49
    Para
    0.48
    ITA
    0.48
    Ë
    0.46
    ga
    0.44
    №
    0.44
    ㎎
    0.44
    xx
    0.44
    
    0.43
    POSITIVE LOGITS
     กี้
    0.43
     relinqu
    0.42
    ινων
    0.42
    atively
    0.41
     silica
    0.40
     Gim
    0.40
     antennae
    0.40
    тие
    0.39
     Dyke
    0.39
    emption
    0.39
    Activations Density 0.011%

    No Known Activations