© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141968
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    \
    1.71
    _
    1.43
    ?
    1.38
    ่า
    1.32
    ی
    1.31
    <
    1.23
     restitu
    1.23
    "*
    1.22
    !
    1.17
    \*
    1.16
    POSITIVE LOGITS
    ла
    1.64
    ен
    1.55
    ਰ
    1.55
    म
    1.52
    a
    1.46
    en
    1.43
    g
    1.41
    ो
    1.39
    ab
    1.37
    le
    1.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.