© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156276
    Prev
    Next
    INDEX
    Explanations

    etc

    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_50_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
     Vij
    0.52
     Luke
    0.46
    Vij
    0.45
    偈
    0.43
    Luke
    0.43
     Stevens
    0.42
     Vishnu
    0.41
     pee
    0.41
     Bij
    0.41
     Ernie
    0.40
    POSITIVE LOGITS
     بالط
    0.44
     Rousseau
    0.40
    स्कार
    0.40
    RB
    0.39
    )\}
    0.37
    Bp
    0.37
    赖
    0.37
     টার
    0.37
    czny
    0.36
    ША
    0.35
    Activations Density 0.002%

    No Known Activations