© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146319
    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_18_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
    -
    0.57
     realistic
    0.57
    ness
    0.49
    ^{
    0.48
     thermal
    0.47
     warm
    0.47
    .
    0.47
    /
    0.46
    es
    0.46
    erva
    0.46
    POSITIVE LOGITS
    ברים
    0.57
    ўні
    0.52
    ᥱ
    0.52
     RULES
    0.51
    ल
    0.51
    ❜
    0.51
     UIScrollView
    0.50
    ન્
    0.49
    ర్ప
    0.49
     ""}
    0.48
    Activations Density 0.000%

    No Known Activations