© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132172
    Prev
    Next
    INDEX
    Explanations

    daily grind

    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
    it
    1.11
    น
    0.96
    ۰
    0.91
     heroic
    0.91
    rik
    0.87
    ри
    0.86
    ων
    0.84
    reate
    0.82
     puree
    0.82
     figurine
    0.81
    POSITIVE LOGITS
    ৯
    1.33
    কে
    1.23
    كار
    1.15
    لي
    1.14
    B
    1.14
    K
    1.05
    إ
    1.04
    З
    1.04
    O
    1.01
    ఎ
    1.01
    Activations Density 0.000%

    No Known Activations