© 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. 121834
    Prev
    Next
    INDEX
    Explanations

    NAMES followed by space or punctuation

    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
    <0x0D>
    0.75
     responde
    0.70
    ாவில்
    0.63
     muros
    0.62
     ressent
    0.60
     чемпиона
    0.59
     affirmat
    0.59
    <0xA8>
    0.59
    可在
    0.59
     vértice
    0.59
    POSITIVE LOGITS
    ת
    0.86
    gning
    0.80
    त
    0.76
    leb
    0.75
    g
    0.72
    و
    0.72
    一
    0.71
    cience
    0.70
    т
    0.70
    の
    0.70
    Activations Density 0.000%

    No Known Activations