© 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. 154109
    Prev
    Next
    INDEX
    Explanations

    phonetic fragments

    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
    gate
    0.40
    crypt
    0.40
    ip
    0.38
    n
    0.38
    cule
    0.38
    ophilus
    0.38
    hood
    0.37
    िको
    0.37
    aceous
    0.36
     ump
    0.35
    POSITIVE LOGITS
    х
    2.69
    き
    1.67
    み
    0.92
    セット
    0.80
    mi
    0.68
    хло
    0.66
    店
    0.64
    хь
    0.63
    хта
    0.61
    χ
    0.58
    Activations Density 0.001%

    No Known Activations