© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88953
    Prev
    Next
    INDEX
    Explanations

    Phanerozoic, Phantasmagoria, Palati, T-shyeocheu

    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_3_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
     dotato
    0.66
     championed
    0.62
     cadeaux
    0.61
    ‰
    0.59
    ቛ
    0.57
    =[];
    0.57
     fattori
    0.56
    profitLoss
    0.56
     habitaciones
    0.55
    arbeitet
    0.55
    POSITIVE LOGITS
     as
    0.75
    re
    0.66
    ร
    0.66
    س
    0.66
    na
    0.63
    top
    0.63
    та
    0.63
    ด
    0.61
    সি
    0.61
    مه
    0.61
    Activations Density 0.000%

    No Known Activations