© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165063
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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_31_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
     buon
    0.38
    sklearn
    0.36
    ­
    0.36
     khusus
    0.35
    ▸
    0.35
     ample
    0.34
    ombie
    0.34
    eron
    0.34
     Discuss
    0.33
     seus
    0.33
    POSITIVE LOGITS
    ものを
    0.38
    家伙
    0.34
    ভাবে
    0.34
    ElementName
    0.32
    lüğ
    0.31
    ものが
    0.31
    ]<?
    0.31
     অবস্থায়
    0.30
    ResourceManager
    0.30
     المستوى
    0.30
    Activations Density 0.006%

    No Known Activations