© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216867
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_47_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
    फोर
    0.40
     올
    0.40
     тай
    0.40
     reprend
    0.40
     skriver
    0.39
    olato
    0.39
    嗥
    0.39
     contador
    0.38
    chromo
    0.38
    重生
    0.38
    POSITIVE LOGITS
     twenty
    0.48
    二十
    0.44
    £
    0.43
     vingt
    0.41
    twenty
    0.40
    aba
    0.38
     fifty
    0.38
     двадцать
    0.38
     Twenty
    0.37
    பட்ட
    0.37
    Activations Density 0.000%

    No Known Activations