© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82929
    Prev
    Next
    INDEX
    Explanations

    graduating

    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_0_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
    h
    1.85
    o
    1.59
    ab
    1.31
     decentral
    1.30
    d
    1.30
    es
    1.25
    c
    1.09
     बाद
    1.09
    ur
    1.06
    ast
    1.05
    POSITIVE LOGITS
    ت
    2.17
    т
    2.09
    4
    1.87
    א
    1.82
     a
    1.73
    5
    1.71
    고
    1.62
    3
    1.61
    н
    1.56
    त
    1.52
    Activations Density 0.001%

    No Known Activations