© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173228
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_20_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
    .¹
    0.51
     Tier
    0.48
     ICS
    0.47
     Generation
    0.46
     číslo
    0.45
    rie
    0.45
     Feeling
    0.45
     протягом
    0.45
    闶
    0.45
     Ont
    0.44
    POSITIVE LOGITS
     auth
    0.44
    سل
    0.42
    博客
    0.42
    嬪
    0.41
     relatos
    0.40
     modos
    0.40
    ौला
    0.39
     antiguas
    0.39
    别人的
    0.39
     pessoais
    0.39
    Activations Density 0.001%

    No Known Activations