© 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. 88412
    Prev
    Next
    INDEX
    Explanations

    cells, T cell

    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
    ка
    0.67
     insolvent
    0.66
    しさ
    0.66
     legenda
    0.63
     perto
    0.61
     Algon
    0.61
    丏
    0.60
     unimagin
    0.59
     सलू
    0.59
    er
    0.59
    POSITIVE LOGITS
    ج
    0.96
    ق
    0.81
    ff
    0.79
    ف
    0.73
    of
    0.72
    Der
    0.66
    მ
    0.63
    Sk
    0.63
    In
    0.61
    Sp
    0.61
    Activations Density 0.005%

    No Known Activations