© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65865
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Jol
    0.42
    เขียน
    0.40
    ფ
    0.40
     Written
    0.40
     write
    0.39
     written
    0.39
     Jay
    0.39
     Schreiben
    0.39
     scritta
    0.38
     Thi
    0.38
    POSITIVE LOGITS
     komma
    0.51
     came
    0.48
    Come
    0.46
     ಬಂದ
    0.46
    Came
    0.46
     come
    0.46
    prime
    0.45
    窄
    0.42
    come
    0.42
    amante
    0.41
    Activations Density 0.000%

    No Known Activations