© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123161
    Prev
    Next
    INDEX
    Explanations

    pinch, Metals, gy, microfilm

    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_3_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
    in
    1.13
    s
    1.04
    𝙨
    0.74
    ра
    0.72
    ों
    0.71
    ä
    0.71
    را
    0.70
    vär
    0.69
     in
    0.68
    es
    0.68
    POSITIVE LOGITS
    Q
    0.80
    B
    0.79
    У
    0.77
    т
    0.73
    ן
    0.73
    Το
    0.72
    ה
    0.72
    י
    0.68
    과
    0.66
     microfilm
    0.66
    Activations Density 0.005%

    No Known Activations