© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52217
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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_30_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
     aforementioned
    0.44
    einander
    0.37
     উল্লেখিত
    0.35
     밝혔
    0.33
     법
    0.33
     mentioned
    0.32
     institutions
    0.32
     Di
    0.32
     belirt
    0.32
     الدي
    0.32
    POSITIVE LOGITS
    古屋
    0.37
     Pik
    0.35
    نین
    0.33
    oshin
    0.32
    λά
    0.32
    %:
    0.32
    არ
    0.32
    天然
    0.32
    䒷
    0.32
     وین
    0.31
    Activations Density 0.040%

    No Known Activations