© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132116
    Prev
    Next
    INDEX
    Explanations

    image quality

    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_50_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
     clandestine
    0.42
    cco
    0.41
     clandest
    0.41
    ሪ
    0.41
     C
    0.40
     illicit
    0.39
     nodal
    0.38
     devez
    0.38
     croup
    0.38
     tal
    0.37
    POSITIVE LOGITS
     Simón
    0.43
    śmy
    0.41
    стра
    0.41
    堃
    0.40
    StringIO
    0.40
     Dolores
    0.39
    ܡܪ
    0.38
    तु
    0.38
    シ
    0.38
     சித்த
    0.38
    Activations Density 0.000%

    No Known Activations