© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3008
    Prev
    Next
    INDEX
    Explanations

    Object.keys or Object.entries

    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_39_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
    untansi
    0.41
     constituer
    0.40
     vocal
    0.40
    洵
    0.40
    FileCopy
    0.39
    VOC
    0.38
    何度
    0.38
     ინ
    0.38
     triggering
    0.38
     multipl
    0.37
    POSITIVE LOGITS
    keys
    0.47
     keys
    0.40
    Assign
    0.35
    Define
    0.35
     bravery
    0.35
    Keys
    0.35
     Disponible
    0.35
     बनाएं
    0.34
    踺
    0.34
    assign
    0.34
    Activations Density 0.003%

    No Known Activations