© 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. 172143
    Prev
    Next
    INDEX
    Explanations

    database connection URLs

    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
    二
    0.42
     二
    0.40
    スク
    0.38
    ાઇલ
    0.38
    プラ
    0.38
    光
    0.37
     ಸಲ
    0.37
    チ
    0.37
    昏
    0.37
    رو
    0.37
    POSITIVE LOGITS
     enthusiastic
    0.48
     Roberto
    0.45
     ఎలా
    0.44
    lında
    0.44
     Lohia
    0.44
     Dont
    0.44
     Cyclic
    0.43
     Postgres
    0.43
     Explain
    0.42
     Robotic
    0.42
    Activations Density 0.000%

    No Known Activations