© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62042
    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_11_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
    ковым
    0.54
    ()}
    0.52
     GLE
    0.52
     Gleason
    0.50
     하며
    0.49
     adopts
    0.47
    WAL
    0.46
    }
    0.46
    려고
    0.45
    GLE
    0.45
    POSITIVE LOGITS
    ס
    0.52
    ീകരിക്ക
    0.51
    cipl
    0.51
    შვ
    0.50
    ఆ
    0.50
     maison
    0.49
    昇
    0.49
     crankshaft
    0.47
    ഷ്യ
    0.46
    אן
    0.46
    Activations Density 0.000%

    No Known Activations