© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37199
    Prev
    Next
    INDEX
    Explanations

    melt away tension

    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_11_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
    ਰ
    0.70
    r
    0.68
    hôte
    0.65
    ਿ
    0.64
    ದೇ
    0.63
    €™
    0.62
    ਿੰ
    0.61
    ਕ
    0.59
    க்கு
    0.57
    ap
    0.57
    POSITIVE LOGITS
    对
    0.72
    随
    0.63
    لي
    0.61
     beam
    0.61
     tiến
    0.60
    tom
    0.59
    он
    0.59
     fromi
    0.59
     transparen
    0.58
     dash
    0.58
    Activations Density 0.003%

    No Known Activations