© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206316
    Prev
    Next
    INDEX
    Explanations

    invalid move or choice

    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_25_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
     端
    0.46
     Samsung
    0.42
     للب
    0.40
    obviously
    0.40
    Samsung
    0.39
     samsung
    0.39
     க
    0.39
     ACR
    0.38
    Falling
    0.38
    Ῥ
    0.38
    POSITIVE LOGITS
    pisah
    0.47
     separate
    0.41
     seperate
    0.40
     separado
    0.40
     coefficients
    0.40
     smoothed
    0.39
    导体
    0.38
     Coefficients
    0.38
     separados
    0.37
    =""/>
    0.36
    Activations Density 0.001%

    No Known Activations