© 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. 45855
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or code blocks

    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
    G
    1.04
    _
    1.03
     be
    0.91
    ’
    0.87
    ']
    0.87
    di
    0.85
    P
    0.85
     at
    0.84
    ↵↵
    0.83
    D
    0.82
    POSITIVE LOGITS
    <0x0D>
    0.75
    </h2>
    0.70
    </h5>
    0.69
    ти
    0.69
    örungen
    0.68
    اهای
    0.68
    也会
    0.66
    рія
    0.65
    న
    0.65
    нува
    0.65
    Activations Density 0.157%

    No Known Activations