© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195603
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
     is
    0.86
     can
    0.86
     et
    0.77
     It
    0.76
    。
    0.74
     for
    0.73
     on
    0.71
    0.70
     it
    0.67
    <0xB7>
    0.65
    POSITIVE LOGITS
    ﺎ
    0.88
    ﻪ
    0.87
    RAchievement
    0.80
    вав
    0.73
     gobier
    0.73
     enquire
    0.73
    ிய
    0.72
     اين
    0.71
     እነዚህ
    0.71
    هاي
    0.71
    Activations Density 0.000%

    No Known Activations