© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213654
    Prev
    Next
    INDEX
    Explanations

    dates

    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_47_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
     шту
    0.45
    ROff
    0.41
    textbackslash
    0.39
     vadati
    0.38
    Ҷ
    0.38
    Hurricane
    0.37
     З
    0.37
    Art
    0.36
     арти
    0.36
     off
    0.35
    POSITIVE LOGITS
     boxed
    0.39
    uttam
    0.39
     करा
    0.38
     المج
    0.38
    옥
    0.38
     permanently
    0.37
     تغ
    0.37
    ೌ
    0.37
    बल
    0.36
    opro
    0.36
    Activations Density 0.000%

    No Known Activations