© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    nestled into / under

    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_13_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
    єте
    0.49
    逾
    0.48
     mesmos
    0.48
     wellness
    0.47
     nostru
    0.46
    援
    0.45
     inserir
    0.45
     escrever
    0.45
    тан
    0.45
     danni
    0.44
    POSITIVE LOGITS
    י
    0.54
    ù
    0.53
    manifolds
    0.52
    SCHRAMM
    0.51
    weight
    0.50
    že
    0.48
    fieldContext
    0.48
    ي
    0.48
    US
    0.47
    Schwarz
    0.47
    Activations Density 0.053%

    No Known Activations