© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201376
    Prev
    Next
    INDEX
    Explanations

    slightly polished

    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_6_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
    .
    0.96
    นิ
    0.86
    าง
    0.81
    น้อย
    0.80
     warden
    0.79
    น
    0.79
    したので
    0.77
    อย่าง
    0.75
     vendor
    0.74
     spoon
    0.73
    POSITIVE LOGITS
    es
    1.66
    en
    1.63
    im
    1.48
    us
    1.34
    and
    1.33
    is
    1.31
    ون
    1.30
    un
    1.27
    е
    1.25
    er
    1.23
    Activations Density 0.003%

    No Known Activations