© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217073
    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_31_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
     czas
    0.46
     spasms
    0.41
     moze
    0.41
     stromal
    0.39
    熾
    0.39
    vgl
    0.37
     focuss
    0.37
     igualdad
    0.37
    诏
    0.37
     equalities
    0.37
    POSITIVE LOGITS
    블릿
    0.36
    Crist
    0.36
    悬
    0.36
    Inventory
    0.35
    W
    0.35
    دە
    0.35
     Bishop
    0.34
    HIT
    0.34
    Written
    0.34
    height
    0.34
    Activations Density 0.000%

    No Known Activations