© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197651
    Prev
    Next
    INDEX
    Explanations

    official

    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_4_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
    ร
    0.45
    an
    0.44
    I
    0.38
    َ
    0.36
    r
    0.36
     hush
    0.35
    ان
    0.34
    st
    0.34
     seda
    0.33
    i
    0.33
    POSITIVE LOGITS
     (
    0.54
    دا
    0.49
    ك
    0.46
    یت
    0.44
    نی
    0.44
    но
    0.42
    ση
    0.42
    다
    0.42
    یز
    0.42
    یم
    0.41
    Activations Density 0.020%

    No Known Activations