© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 173678
    Prev
    Next
    INDEX
    Explanations

    class or map definitions

    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
    }}
    0.13
     O
    0.13
    O
    0.13
    omar
    0.13
     Gu
    0.13
     as
    0.12
     mc
    0.12
    jac
    0.12
     Ragnar
    0.12
    us
    0.12
    POSITIVE LOGITS
    ethanol
    0.15
    ټبال
    0.15
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.14
    ➎
    0.14
    ઢી
    0.13
     forbidding
    0.13
    你就
    0.13
     multimillion
    0.13
     soliton
    0.13
     isotonic
    0.13
    Activations Density 0.002%

    No Known Activations