© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7669
    Prev
    Next
    INDEX
    Explanations

    road, streets, path, lead

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    জনাব
    0.40
     pendek
    0.39
     corto
    0.38
     converters
    0.38
     curto
    0.36
    short
    0.35
    ="))
    0.35
     Converter
    0.35
     SHORT
    0.35
    faat
    0.34
    POSITIVE LOGITS
    elta
    0.38
     cruciate
    0.37
     stick
    0.36
     reprim
    0.35
     still
    0.35
    ɽ
    0.34
     porridge
    0.34
    Mol
    0.33
    ፈላ
    0.33
    August
    0.33
    Activations Density 0.020%

    No Known Activations