© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61638
    Prev
    Next
    INDEX
    Explanations

    new

    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
    KeepOriginal
    0.40
    Iy
    0.37
    ly
    0.36
    ritas
    0.36
    ಲಿ
    0.36
    Scrim
    0.36
    ㅔ
    0.36
    ᅦ
    0.36
    젊
    0.35
    jorie
    0.35
    POSITIVE LOGITS
    by
    0.63
    be
    0.60
    bs
    0.58
     players
    0.57
     consumers
    0.55
    bt
    0.53
     engineers
    0.52
     com
    0.52
     ar
    0.52
     students
    0.51
    Activations Density 0.002%

    No Known Activations