© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23940
    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_56_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
     chosen
    0.39
    chosen
    0.38
    threatening
    0.37
     escolh
    0.35
     „
    0.35
     Carlo
    0.34
    were
    0.34
    !("
    0.34
    „
    0.34
    ッチ
    0.34
    POSITIVE LOGITS
     been
    1.18
    Been
    1.16
     Been
    1.08
    been
    1.07
     BEEN
    1.07
     geweest
    0.82
     ollut
    0.80
     været
    0.73
     داشته
    0.70
     vært
    0.69
    Activations Density 0.000%

    No Known Activations