© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33257
    Prev
    Next
    INDEX
    Explanations

    a href links

    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_31_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
    붙
    0.40
     solidification
    0.39
    ériment
    0.37
    apply
    0.34
     affirmations
    0.34
    ஆம்
    0.34
    твер
    0.34
     maturity
    0.33
    해보
    0.33
     limitations
    0.33
    POSITIVE LOGITS
    VideoStream
    0.42
     HomeComponent
    0.39
    Target
    0.38
    Weblinks
    0.38
    LOTRE
    0.38
    洋
    0.38
     breit
    0.38
     Target
    0.37
     Rath
    0.36
     Wem
    0.36
    Activations Density 0.001%

    No Known Activations