© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259918
    Prev
    Next
    INDEX
    Explanations

    how to instruction

    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_22_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
    ID
    0.25
     scenario
    0.25
    -
    0.25
    交付
    0.25
    asone
    0.25
     kind
    0.24
     reduction
    0.24
     visibility
    0.24
     yellowish
    0.24
    ];
    0.23
    POSITIVE LOGITS
     ಶೆ
    0.30
    ໊
    0.29
    禇
    0.29
     BasicContainer
    0.27
    imleri
    0.26
    ('/:
    0.26
    mathemat
    0.26
    لقه
    0.26
    मॉडल
    0.26
    শকা
    0.25
    Activations Density 0.029%

    No Known Activations