© 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. 13788
    Prev
    Next
    INDEX
    Explanations

    beyond or for

    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
    V
    0.71
    H
    0.64
    W
    0.55
    U
    0.54
    S
    0.51
    ua
    0.50
     {
    0.49
    <0x92>
    0.49
    C
    0.48
    Ни
    0.47
    POSITIVE LOGITS
     includ
    0.52
     manipulate
    0.52
     сна
    0.51
     operand
    0.48
     явно
    0.47
     usage
    0.47
     יל
    0.47
     directs
    0.46
     הל
    0.46
     wandering
    0.46
    Activations Density 0.073%

    No Known Activations