© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9019
    Prev
    Next
    INDEX
    Explanations

    resolution, size, with legal entity, A4

    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_13_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
     depression
    0.38
     terrified
    0.37
     prel
    0.36
     depressions
    0.36
     {
    0.35
     Kendrick
    0.35
    }{
    0.35
     readings
    0.34
    âne
    0.34
    بر
    0.33
    POSITIVE LOGITS
    subset
    0.40
    ／
    0.39
     Cómo
    0.37
     размере
    0.37
    vim
    0.37
    yacute
    0.37
    zwischen
    0.37
     scaleOf
    0.36
    irán
    0.36
    ujete
    0.35
    Activations Density 0.033%

    No Known Activations