© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174628
    Prev
    Next
    INDEX
    Explanations

    forums and related online communities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    ných
    0.33
    راضي
    0.33
     ausreiche
    0.32
     zariaden
    0.32
     barges
    0.31
     peralatan
    0.31
     ነበር
    0.29
    缸
    0.29
    製造
    0.28
     миллиар
    0.28
    POSITIVE LOGITS
    Finger
    0.38
    Common
    0.37
    Hum
    0.32
    Ge
    0.32
    angwa
    0.31
     Common
    0.31
    Modal
    0.31
     Penit
    0.31
    ווה
    0.30
    Bien
    0.30
    Activations Density 0.001%

    No Known Activations