© 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
    2. Gemma-3-27B-IT
    3. 9-GEMMASCOPE-2-TRANSCODER-262K
    4. 199121
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
     can
    0.51
     of
    0.50
     OF
    0.47
     in
    0.46
     figure
    0.44
    of
    0.44
     pathogenicity
    0.43
    k
    0.43
     formulation
    0.43
    g
    0.43
    POSITIVE LOGITS
    фель
    0.59
    дэ
    0.58
     Omphalodes
    0.55
     অন্যের
    0.53
     izquier
    0.52
     உங்கள்
    0.52
     revistas
    0.51
     registrados
    0.51
     Einwill
    0.51
    nagyobb
    0.51
    Activations Density 0.000%

    No Known Activations