© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86658
    Prev
    Next
    INDEX
    Explanations

    sync, cloud, CX, software

    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_3_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
    ל
    0.74
     wilfully
    0.64
    שת
    0.60
    شي
    0.59
    getAsJsonObject
    0.59
    有个
    0.57
    IdleSync
    0.57
    MJX
    0.56
    عي
    0.55
    سو
    0.55
    POSITIVE LOGITS
     I
    0.82
    finals
    0.73
    essential
    0.71
    exploration
    0.70
    education
    0.68
    off
    0.67
    energy
    0.67
    nucleus
    0.67
    apples
    0.66
    homes
    0.65
    Activations Density 0.000%

    No Known Activations