© 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. 249752
    Prev
    Next
    INDEX
    Explanations

    say jacks

    np_max-act-logits · gemini-2.5-flash-lite
    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
     j
    0.62
     ج
    0.43
     ज
    0.42
    󠁧
    0.42
    谲
    0.38
    тере
    0.38
     J
    0.37
    ڇ
    0.37
     scares
    0.37
     تعمل
    0.36
    POSITIVE LOGITS
    kf
    0.38
    ocom
    0.37
    ark
    0.37
     got
    0.36
    f
    0.36
     right
    0.35
     rack
    0.34
     გას
    0.34
     berk
    0.33
    ielt
    0.33
    Activations Density 0.000%

    No Known Activations