© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251682
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
     Archipelago
    0.38
    )}$,
    0.35
     Dur
    0.35
     kom
    0.34
    çar
    0.34
    Kom
    0.33
     verletzt
    0.33
    ຳ
    0.33
     देयर
    0.32
     كوم
    0.32
    POSITIVE LOGITS
     po
    0.90
     pa
    0.86
     ca
    0.85
     fa
    0.84
     pla
    0.83
     mo
    0.79
     fo
    0.79
     fi
    0.78
     ba
    0.78
     hea
    0.76
    Activations Density 0.003%

    No Known Activations