© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144029
    Prev
    Next
    INDEX
    Explanations

    soft * consultant

    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
    us
    1.74
    ur
    1.63
    ro
    1.53
    v
    1.53
    ل
    1.48
    M
    1.47
    H
    1.34
    d
    1.33
    P
    1.33
    開催
    1.32
    POSITIVE LOGITS
     in
    1.48
     aument
    1.34
    ט
    1.31
    या
    1.29
    트를
    1.27
     aumentando
    1.26
    도
    1.26
    an
    1.25
    ی
    1.25
    ก
    1.22
    Activations Density 0.000%

    No Known Activations