© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31233
    Prev
    Next
    INDEX
    Explanations

    Harper Lee's To Kill a Mockingbird

    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_7_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
    -
    0.93
    ore
    0.90
    <0xA0>
    0.88
    (
    0.82
    and
    0.81
    м
    0.81
    ha
    0.80
    ina
    0.80
    ia
    0.79
    yll
    0.77
    POSITIVE LOGITS
     I
    1.01
     is
    1.00
     interno
    0.96
     électronique
    0.93
    其他
    0.91
     advertise
    0.89
     entertain
    0.89
     malice
    0.88
     entitle
    0.85
    이지만
    0.85
    Activations Density 0.000%

    No Known Activations