© 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. 88144
    Prev
    Next
    INDEX
    Explanations

    Carly Rae Jepsen

    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
    ’
    0.88
    at
    0.82
    a
    0.68
    ́s
    0.67
    os
    0.67
    as
    0.66
     in
    0.66
    B
    0.65
    og
    0.63
    ak
    0.61
    POSITIVE LOGITS
    િ
    0.82
    ﺎ
    0.75
    ле
    0.74
     transporte
    0.70
     expel
    0.69
     endangering
    0.68
    າ
    0.67
    いで
    0.66
     Antônio
    0.66
    って
    0.66
    Activations Density 0.012%

    No Known Activations