© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179608
    Prev
    Next
    INDEX
    Explanations

    .

    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_24_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
     überw
    0.32
    фом
    0.27
    ତି
    0.26
     hauptsächlich
    0.26
    𝐛
    0.25
     बेसिकली
    0.25
    DisplayStyle
    0.25
    nessy
    0.24
    য়নের
    0.24
     nytt
    0.24
    POSITIVE LOGITS
     G
    0.24
     Gal
    0.24
     Arm
    0.23
     Infra
    0.23
     Gr
    0.22
     infra
    0.22
     L
    0.22
     S
    0.22
     Este
    0.22
     कॉ
    0.22
    Activations Density 0.003%

    No Known Activations