© 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. 79786
    Prev
    Next
    INDEX
    Explanations

    FUSE

    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
    ни
    1.41
    들이
    1.39
    ेट
    1.26
    োস
    1.20
    و
    1.19
    ہ
    1.10
    os
    1.09
    ys
    1.09
    The
    1.08
    etti
    1.08
    POSITIVE LOGITS
     be
    1.77
     {
    1.64
     a
    1.55
    ר
    1.45
    та
    1.36
     concili
    1.36
     agregado
    1.34
    ;
    1.34
    р
    1.31
     verduras
    1.30
    Activations Density 0.000%

    No Known Activations