© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137218
    Prev
    Next
    INDEX
    Explanations

    java -jar command

    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
    or
    0.58
    id
    0.56
    elling
    0.56
    ar
    0.52
     n
    0.50
    ryn
    0.49
    ieves
    0.49
    lo
    0.48
    Length
    0.48
    eyer
    0.48
    POSITIVE LOGITS
    ЕН
    0.57
     DNIs
    0.52
     அலு
    0.52
    榖
    0.50
     lavoratori
    0.50
    葵
    0.49
    めでとう
    0.48
    𝘮
    0.48
     surgeries
    0.48
     AGRIC
    0.48
    Activations Density 0.000%

    No Known Activations