© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38471
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    衮
    0.49
    themem
    0.43
     `=`,
    0.41
    gning
    0.40
    Ⲩ
    0.40
     PT
    0.39
    𝑁
    0.39
    Greek
    0.39
     também
    0.38
    GN
    0.38
    POSITIVE LOGITS
     th
    0.41
     inserting
    0.37
     cé
    0.36
     hơi
    0.35
    acán
    0.34
     ensue
    0.33
     n
    0.33
    軒
    0.32
    illac
    0.32
    라도
    0.32
    Activations Density 0.003%

    No Known Activations