© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132573
    Prev
    Next
    INDEX
    Explanations

    called a

    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_6_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
    0.79
    ן
    0.75
    ุ
    0.73
    ו
    0.73
    та
    0.72
    บ
    0.64
    на
    0.64
     toque
    0.64
    น
    0.64
     mesmer
    0.63
    POSITIVE LOGITS
    ag
    0.83
    ind
    0.81
    ens
    0.75
    ups
    0.73
    ere
    0.73
    ys
    0.73
    clinical
    0.71
    ries
    0.70
    ins
    0.69
    ü
    0.66
    Activations Density 0.003%

    No Known Activations