© 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. 46861
    Prev
    Next
    INDEX
    Explanations

    escape velocity or method

    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
    ian
    0.81
     i
    0.71
    ing
    0.70
    am
    0.68
    <0x80>
    0.68
     hoops
    0.68
    0.66
    ya
    0.63
     an
    0.63
    ed
    0.62
    POSITIVE LOGITS
    ه
    0.82
    ۔
    0.71
    는
    0.69
     نجي
    0.67
    י
    0.65
    هرب
    0.65
    ’
    0.65
    قیم
    0.62
     podendo
    0.62
    setString
    0.61
    Activations Density 0.064%

    No Known Activations