© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39940
    Prev
    Next
    INDEX
    Explanations

    code

    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
     located
    0.50
    located
    0.43
     (
    0.41
     henceforth
    0.41
     ("
    0.38
     (“
    0.37
     found
    0.37
     helps
    0.37
    ственными
    0.37
     (‘
    0.36
    POSITIVE LOGITS
    роме
    0.40
    ̮
    0.36
     ஈ
    0.36
     অফিসার
    0.35
    etch
    0.35
     Роз
    0.35
    supseteq
    0.35
     Thương
    0.35
    utacji
    0.34
    inato
    0.34
    Activations Density 0.064%

    No Known Activations