© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82810
    Prev
    Next
    INDEX
    Explanations

    Bay Area, Baywatch

    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_0_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
    :
    1.05
    و
    0.93
    서
    0.81
    ,
    0.80
    </h2>
    0.77
    O
    0.74
     మరియు
    0.73
    I
    0.73
    ો
    0.73
    اة
    0.71
    POSITIVE LOGITS
    ل
    1.34
    a
    1.23
    ad
    1.20
    is
    1.14
    an
    1.08
    increases
    1.06
     for
    1.04
    ر
    1.02
     notificación
    1.00
    iswa
    0.99
    Activations Density 0.001%

    No Known Activations