© 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. 239239
    Prev
    Next
    INDEX
    Explanations

    single, one, half

    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
     പൂര്‍
    0.41
     entanglement
    0.40
     completely
    0.39
     pulpit
    0.39
    ☮
    0.38
    XO
    0.38
     completamente
    0.37
     mend
    0.37
     boca
    0.36
     pants
    0.36
    POSITIVE LOGITS
    单
    0.80
    single
    0.72
     Single
    0.72
    シングル
    0.72
     SINGLE
    0.70
     シングル
    0.69
    Single
    0.67
    単
    0.65
     single
    0.63
    SINGLE
    0.62
    Activations Density 0.019%

    No Known Activations