© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140435
    Prev
    Next
    INDEX
    Explanations

    rather than

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    掇
    0.38
     алы
    0.36
    eland
    0.36
    Invit
    0.36
    мель
    0.36
    ensible
    0.35
    选取
    0.35
    舉
    0.35
     impracticable
    0.34
    fn
    0.34
    POSITIVE LOGITS
     versuchen
    0.50
     Rather
    0.46
     rather
    0.45
     pokuš
    0.45
     mencoba
    0.43
     plutôt
    0.42
     försö
    0.42
     tudo
    0.42
     Trying
    0.41
     respondió
    0.41
    Activations Density 0.006%

    No Known Activations