© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146680
    Prev
    Next
    INDEX
    Explanations

    v

    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_59_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
     MACHINIST
    0.40
    colour
    0.38
    ज
    0.37
    ने
    0.36
    considered
    0.36
    जिसे
    0.35
     bullshit
    0.35
    Folder
    0.35
    מש
    0.34
     argentino
    0.34
    POSITIVE LOGITS
    u
    0.59
     __
    0.51
    抧
    0.50
    p
    0.48
     :-
    0.47
     E
    0.46
     P
    0.46
     ___
    0.46
     Seven
    0.45
    q
    0.45
    Activations Density 0.000%

    No Known Activations