© 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. 34304
    Prev
    Next
    INDEX
    Explanations

    names like Cameron, Gibson, Henson

    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
    A
    0.66
    ‘’
    0.64
    1
    0.63
    ximately
    0.63
    I
    0.63
    on
    0.63
    ’
    0.62
    et
    0.61
    ’”
    0.61
    ≣
    0.61
    POSITIVE LOGITS
    ми
    0.86
    。
    0.66
     geist
    0.61
     Präsident
    0.59
    ٣
    0.57
    ил
    0.56
    gebaut
    0.55
     világ
    0.55
     puisse
    0.54
     rozwiąz
    0.54
    Activations Density 0.000%

    No Known Activations