© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196715
    Prev
    Next
    INDEX
    Explanations

    divergência, talented, ironic, verb, him

    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_9_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
    라인
    0.60
    ćeg
    0.57
     마음
    0.53
     kojem
    0.52
    тости
    0.52
     라
    0.50
    ³)
    0.50
     Príncipe
    0.50
    홧
    0.50
    ූප
    0.49
    POSITIVE LOGITS
    I
    0.57
    IT
    0.52
    D
    0.52
    V
    0.52
    B
    0.50
    ENT
    0.50
    0
    0.50
    IV
    0.49
    Discussion
    0.49
    =
    0.48
    Activations Density 0.000%

    No Known Activations