© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195958
    Prev
    Next
    INDEX
    Explanations

    say "="

    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_46_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
    added
    0.41
    Upp
    0.38
     added
    0.36
     Added
    0.36
    ურნ
    0.35
     runways
    0.35
    垮
    0.35
     toege
    0.35
    derm
    0.34
    獰
    0.34
    POSITIVE LOGITS
     Equilib
    0.40
    нак
    0.38
     combien
    0.38
     равно
    0.38
     prime
    0.36
    균
    0.36
     PRIME
    0.36
    ಿಕೆ
    0.36
    venuti
    0.35
    ógio
    0.35
    Activations Density 0.007%

    No Known Activations