© 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. 202602
    Prev
    Next
    INDEX
    Explanations

    formula for last term

    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
    THAT
    0.48
    Arabic
    0.43
    Duplicates
    0.43
    ala
    0.42
    t
    0.42
    global
    0.42
    Sah
    0.42
    <^
    0.41
    ♫
    0.41
    af
    0.41
    POSITIVE LOGITS
    '
    0.42
    関
    0.41
    yzed
    0.40
     vencedor
    0.40
     demoral
    0.39
    uação
    0.38
    кован
    0.38
     резер
    0.38
     במהלך
    0.38
     collapsed
    0.38
    Activations Density 0.000%

    No Known Activations