© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15317
    Prev
    Next
    INDEX
    Explanations

    build and import statements

    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_40_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
     scan
    0.73
     Scan
    0.70
    scan
    0.69
     sweep
    0.69
     scans
    0.68
    Scan
    0.64
     sweeps
    0.64
    扫
    0.64
     Sweep
    0.63
    掃
    0.62
    POSITIVE LOGITS
     plummet
    0.38
     granite
    0.37
     설치
    0.37
    token
    0.37
    Token
    0.37
     installations
    0.36
     Granite
    0.35
    বাম
    0.35
    Encoded
    0.35
    rgb
    0.35
    Activations Density 0.252%

    No Known Activations