© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193649
    Prev
    Next
    INDEX
    Explanations

    service level agreements

    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_4_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
    r
    0.88
     It
    0.86
    ched
    0.79
    はない
    0.73
    ed
    0.71
    elves
    0.67
    an
    0.65
    л
    0.62
    出す
    0.61
     They
    0.60
    POSITIVE LOGITS
    <0x0D>
    1.18
    <h4>
    0.83
    RU
    0.82
    Penumpang
    0.81
    ка
    0.80
    は
    0.80
    Classe
    0.79
    PARTY
    0.77
     Controle
    0.77
    '
    0.77
    Activations Density 0.059%

    No Known Activations