© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103898
    Prev
    Next
    INDEX
    Explanations

    mr followed by names or rn followed by punctuation

    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_1_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
    2
    1.13
    ;
    1.10
     of
    1.01
    <
    1.01
    ='
    0.96
    แต่
    0.90
    ..
    0.89
     metabolism
    0.88
     =
    0.88
     spectroscopy
    0.87
    POSITIVE LOGITS
    يا
    1.30
    is
    1.29
    حي
    1.25
     ي
    1.20
    ش
    1.16
    وك
    1.09
    دي
    1.07
    هي
    1.05
    re
    1.04
    т
    1.04
    Activations Density 0.001%

    No Known Activations