© 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. 92631
    Prev
    Next
    INDEX
    Explanations

    ib

    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
    رت
    0.52
    ρφ
    0.46
    رة
    0.43
    ﻻ
    0.43
    rk
    0.42
    rée
    0.41
    rf
    0.41
    رى
    0.41
    рга
    0.40
    ръ
    0.40
    POSITIVE LOGITS
    ean
    0.76
    ei
    0.75
    ej
    0.70
    ein
    0.70
    t
    0.68
    l
    0.68
    eer
    0.67
    eas
    0.67
    eu
    0.64
    eat
    0.63
    Activations Density 0.001%

    No Known Activations