© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58747
    Prev
    Next
    INDEX
    Explanations

    URLs containing "/en/"

    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_2_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
    ุ
    1.46
    ↵↵
    1.34
    es
    1.31
    is
    1.30
    isasi
    1.27
    F
    1.27
    to
    1.22
    ↵
    1.18
    G
    1.17
    H
    1.16
    POSITIVE LOGITS
    н
    1.63
    ،
    1.21
     μία
    1.20
    نيا
    1.19
    你
    1.19
    ру
    1.18
    ட்
    1.14
     دي
    1.13
    :
    1.09
    ன்
    1.07
    Activations Density 0.000%

    No Known Activations