© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223783
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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_10_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
    \
    0.79
    ﻦ
    0.77
    </h3>
    0.72
    Team
    0.71
    ij
    0.69
    +
    0.69
    Trend
    0.65
    '
    0.64
    iert
    0.64
    Mid
    0.63
    POSITIVE LOGITS
    ло
    0.71
    l
    0.70
    точ
    0.70
    ovaniyu
    0.69
    لیک
    0.66
    蔵
    0.66
     Gori
    0.65
    لت
    0.64
    лені
    0.63
    lcii
    0.63
    Activations Density 0.001%

    No Known Activations