© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139785
    Prev
    Next
    INDEX
    Explanations

    well-commented code examples

    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_12_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
    IA
    0.58
    HA
    0.56
    ATE
    0.54
    าล
    0.54
    <
    0.53
    AL
    0.52
    {
    0.52
    ANG
    0.49
     IL
    0.49
    HI
    0.48
    POSITIVE LOGITS
    θ
    0.59
    ivasena
    0.58
     ಶಿವ
    0.58
     সমস্যায়
    0.58
     viagens
    0.56
     aort
    0.56
     функций
    0.55
    ateurs
    0.54
    neurons
    0.54
    ಾರಂಭ
    0.54
    Activations Density 0.000%

    No Known Activations