© 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. 20221
    Prev
    Next
    INDEX
    Explanations

    greek letters

    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
     XX
    0.77
    XX
    0.74
     xx
    0.73
     photoc
    0.73
     Х
    0.70
    XXX
    0.70
     X
    0.68
     xxx
    0.66
     XXX
    0.66
    XXXXXXXX
    0.65
    POSITIVE LOGITS
     شي
    0.60
     ξ
    0.59
     ज़
    0.57
     §
    0.52
     ksi
    0.52
     КС
    0.51
     ز
    0.50
     ਜ਼
    0.50
     Ksi
    0.50
    샤
    0.48
    Activations Density 0.028%

    No Known Activations