© 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. 138757
    Prev
    Next
    INDEX
    Explanations

    state

    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
     ۱۰
    0.51
    ביע
    0.50
    و
    0.50
     یار
    0.50
     Из
    0.49
    Из
    0.48
     devoir
    0.47
     ലി
    0.47
    ده
    0.46
    იმ
    0.46
    POSITIVE LOGITS
    蕖
    0.50
    áció
    0.47
    spiracy
    0.47
    spring
    0.46
     attacked
    0.46
    </sup>
    0.45
    akas
    0.45
    ierung
    0.44
    mern
    0.44
    mann
    0.44
    Activations Density 0.000%

    No Known Activations