© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48954
    Prev
    Next
    INDEX
    Explanations

    variables

    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_55_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
     Strings
    0.57
    strings
    0.52
    Strings
    0.49
     strings
    0.49
     Configurations
    0.46
    Dictionaries
    0.45
    Vectors
    0.42
     `{
    0.40
     vectors
    0.40
     params
    0.39
    POSITIVE LOGITS
    变量
    0.49
     Held
    0.47
    held
    0.47
     variable
    0.45
    variable
    0.45
     drž
    0.44
     held
    0.43
     variabile
    0.43
    Held
    0.43
     holde
    0.43
    Activations Density 0.014%

    No Known Activations