© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153370
    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_23_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
    ।
    0.52
    ん
    0.48
    insurance
    0.47
     glazed
    0.46
     smiled
    0.46
     snatch
    0.46
     snatched
    0.45
    皁
    0.45
     singled
    0.44
     pastes
    0.44
    POSITIVE LOGITS
    یتے
    0.48
    ulier
    0.44
     chief
    0.42
    ium
    0.42
    ిక
    0.41
    nent
    0.41
    ьи
    0.41
     단위
    0.40
     productividad
    0.39
    变革
    0.39
    Activations Density 0.000%

    No Known Activations