© 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. 150737
    Prev
    Next
    INDEX
    Explanations

    8

    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
     Opin
    0.39
    ²+
    0.38
    imum
    0.38
     Wiener
    0.38
     Rin
    0.37
    2
    0.37
     De
    0.37
     Cart
    0.37
    والفق
    0.37
    andr
    0.36
    POSITIVE LOGITS
    ナ
    0.44
    න
    0.39
    D
    0.38
    nta
    0.37
    d
    0.37
    nova
    0.37
    nop
    0.37
    CV
    0.36
    لت
    0.36
    ná
    0.36
    Activations Density 0.000%

    No Known Activations