© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23507
    Prev
    Next
    INDEX
    Explanations

    ---

    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_56_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
     re
    0.80
     dis
    0.59
     재
    0.54
     ре
    0.50
     red
    0.44
    dis
    0.43
     Dis
    0.42
    재
    0.40
     Re
    0.40
     schme
    0.39
    POSITIVE LOGITS
    Acknowledgment
    0.38
    Fors
    0.37
    :(
    0.37
    “[
    0.37
    Assignment
    0.37
    },"
    0.37
    ជា
    0.36
     خانو
    0.36
    Entire
    0.35
    Chill
    0.34
    Activations Density 0.001%

    No Known Activations