© 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. 141784
    Prev
    Next
    INDEX
    Explanations

    Contractor shall/status

    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
    ка
    1.47
    र
    1.30
    க்கு
    1.27
    り
    1.25
    KU
    1.21
    ০০
    1.13
     の
    1.12
    ام
    1.11
    て
    1.11
    DE
    1.09
    POSITIVE LOGITS
    k
    2.17
    é
    1.91
    il
    1.60
    ir
    1.45
    í
    1.40
    ется
    1.33
    y
    1.33
    uc
    1.29
    <0xBF>
    1.28
    ri
    1.28
    Activations Density 0.001%

    No Known Activations