© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151194
    Prev
    Next
    INDEX
    Explanations

    sounds or syllables

    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_60_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
    该
    0.40
    該
    0.39
     عق
    0.38
    :":
    0.38
    $...
    0.38
    ubj
    0.38
     Guzman
    0.38
    .|__
    0.37
    uxxxx
    0.37
     বৎসরের
    0.37
    POSITIVE LOGITS
     DU
    0.64
     SU
    0.63
    ru
    0.60
    du
    0.58
    ли
    0.55
    DU
    0.55
     n
    0.54
    mu
    0.54
     RU
    0.54
     CU
    0.52
    Activations Density 0.002%

    No Known Activations