© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164659
    Prev
    Next
    INDEX
    Explanations

    action steps for resolution

    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
     සැල
    0.40
     කරන්න
    0.33
     নির্মাতা
    0.33
    InBackground
    0.33
     registry
    0.32
    நாயக
    0.32
    জমেন্ট
    0.31
    桃
    0.31
    提供
    0.30
     incubator
    0.30
    POSITIVE LOGITS
    ăzi
    0.41
     Secondo
    0.37
     secondo
    0.34
     replicas
    0.34
     transg
    0.33
     according
    0.33
    💸
    0.33
    ²)
    0.32
    according
    0.32
     Mifflin
    0.32
    Activations Density 0.003%

    No Known Activations