© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195909
    Prev
    Next
    INDEX
    Explanations

    action, dialogue, or descriptive cues

    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_26_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
    Json
    0.45
    льній
    0.41
    ileg
    0.41
    Bibitem
    0.39
    Script
    0.38
     noires
    0.38
     enviado
    0.38
    }"/>
    0.38
    ība
    0.37
    แก้ไข
    0.37
    POSITIVE LOGITS
     چھ
    0.50
    割り
    0.49
    س
    0.49
    mektedir
    0.47
     BIT
    0.46
     diameters
    0.45
     Almost
    0.43
     अन्
    0.42
     alligator
    0.42
     mald
    0.42
    Activations Density 0.000%

    No Known Activations