© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139653
    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_12_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
     fist
    0.52
    
    0.48
    무
    0.47
     Jedi
    0.46
    </u>
    0.46
    <0xB9>
    0.46
    REFLECTION
    0.46
     chilled
    0.45
     cứ
    0.45
     Stealth
    0.44
    POSITIVE LOGITS
    o
    0.89
    ো
    0.59
    en
    0.57
    ed
    0.55
    ו
    0.55
    formas
    0.54
     ores
    0.53
    r
    0.53
    ol
    0.51
    ал
    0.51
    Activations Density 0.000%

    No Known Activations