© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144113
    Prev
    Next
    INDEX
    Explanations

    virtual followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ling
    1.28
    ﻣ
    1.18
    \
    1.09
    িন
    1.07
    -
    1.07
    و
    1.07
    '
    1.06
    ژگی
    1.05
    i
    1.05
    ulence
    1.04
    POSITIVE LOGITS
    ش
    2.23
    an
    2.09
    ان
    1.73
    of
    1.70
    R
    1.70
     (
    1.66
    기
    1.66
     at
    1.63
     and
    1.50
     for
    1.50
    Activations Density 0.001%

    No Known Activations