© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22678
    Prev
    Next
    INDEX
    Explanations

    divine hope and power

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    classname
    0.40
    gnu
    0.36
    \;\
    0.35
     Bedi
    0.35
    http
    0.34
    astes
    0.34
    ೆಯ
    0.33
     ဖြစ်
    0.33
     microorgan
    0.33
     Kingdoms
    0.33
    POSITIVE LOGITS
     breath
    0.74
    breath
    0.63
     Breath
    0.59
    Breath
    0.57
     generously
    0.44
     rest
    0.43
    অভ
    0.39
    |}{
    0.38
     CONTRIBUTORS
    0.36
    气息
    0.36
    Activations Density 0.040%

    No Known Activations