© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43126
    Prev
    Next
    INDEX
    Explanations

    not every

    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
     I
    1.10
    '
    0.93
    0.93
    el
    0.77
             
    0.73
     Glove
    0.72
     (
    0.72
     Limitations
    0.71
    \*
    0.71
     Specification
    0.71
    POSITIVE LOGITS
    0
    0.97
    extrémité
    0.75
    ین
    0.72
     eradicate
    0.71
    ０
    0.71
    telefono
    0.68
    𝟎
    0.68
     পরে
    0.68
    ！】
    0.67
    𝗘
    0.66
    Activations Density 0.002%

    No Known Activations