© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38505
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     No
    0.51
     O
    0.48
    No
    0.42
    O
    0.37
     o
    0.34
     V
    0.33
     N
    0.33
     но
    0.33
     ओ
    0.32
     dimensional
    0.31
    POSITIVE LOGITS
    ктора
    0.35
    ತ್ತು
    0.33
    ържа
    0.31
    过了
    0.31
    átky
    0.31
    ળી
    0.31
    стре
    0.31
    got
    0.30
    тором
    0.30
     آئ
    0.30
    Activations Density 0.000%

    No Known Activations