© 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. 178119
    Prev
    Next
    INDEX
    Explanations

    market types and scales

    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
    ＆
    0.88
     एवं
    0.86
     &
    0.75
     অ্যান্ড
    0.70
     및
    0.69
    &
    0.67
    및
    0.67
    และ
    0.63
     و
    0.62
     ও
    0.62
    POSITIVE LOGITS
     сложно
    0.36
     heroic
    0.35
     probationary
    0.35
    Ꮞ
    0.35
     frail
    0.34
     seductive
    0.33
     confidential
    0.33
     structurally
    0.33
     Untold
    0.32
     cumbersome
    0.32
    Activations Density 0.861%

    No Known Activations