© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204313
    Prev
    Next
    INDEX
    Explanations

    lift actions and related phrases

    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_6_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
    ים
    0.94
    ੍ਰ
    0.91
    سل
    0.88
    in
    0.84
    र्स
    0.82
    ем
    0.78
    क्स
    0.76
    ਨ
    0.75
     veg
    0.74
    ุน
    0.74
    POSITIVE LOGITS
    abouts
    0.98
    ب
    0.93
    ed
    0.92
    ag
    0.91
    b
    0.89
    is
    0.88
    ek
    0.88
    a
    0.86
    i
    0.86
    ação
    0.85
    Activations Density 0.000%

    No Known Activations