© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214934
    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_5_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
    '
    1.57
    R
    1.45
    ม
    1.29
    (
    1.19
    न
    1.17
    D
    1.16
    H
    1.13
    "
    1.13
    น
    1.13
    on
    1.09
    POSITIVE LOGITS
    டன்
    1.15
    ARCHIVO
    1.07
    padă
    1.05
    vVertex
    1.05
    скетбол
    1.04
    ماً
    1.02
    larghezza
    1.02
    шению
    1.01
    ală
    0.99
    廖
    0.99
    Activations Density 0.000%

    No Known Activations