© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 60877
    Prev
    Next
    INDEX
    Explanations

    data preparation

    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_59_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
    ":"
    0.47
    ()):
    0.44
    thati
    0.43
    ":
    0.43
    "]:
    0.42
    strokes
    0.39
    }:${
    0.38
     ="
    0.37
     =(
    0.37
    ילו
    0.37
    POSITIVE LOGITS
     And
    0.66
    And
    0.61
    ↵↵
    0.47
     Code
    0.46
     Class
    0.46
     Six
    0.43
     Phase
    0.43
     School
    0.43
     Regulations
    0.43
    Revised
    0.43
    Activations Density 0.011%

    No Known Activations