© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125032
    Prev
    Next
    INDEX
    Explanations

    Hot Girl, Road, canvas

    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_37_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
    Spawn
    0.42
     clap
    0.40
    Mk
    0.39
     clapping
    0.38
     Species
    0.37
    usize
    0.36
    mk
    0.36
    Ω
    0.36
    Value
    0.35
    spawn
    0.35
    POSITIVE LOGITS
     онлайн
    0.45
    ለመ
    0.40
    🦵
    0.40
     online
    0.39
     कॉलम
    0.39
     Detox
    0.37
     Онлайн
    0.37
    ગર
    0.37
    ボル
    0.37
     detox
    0.36
    Activations Density 0.002%

    No Known Activations