© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200708
    Prev
    Next
    INDEX
    Explanations

    paved trail or road

    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_6_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
    ни
    0.95
    نا
    0.84
    чи
    0.79
    м
    0.74
    ми
    0.73
    될
    0.73
    ni
    0.72
     shadowy
    0.72
    ких
    0.71
    다
    0.71
    POSITIVE LOGITS
    H
    1.38
    0
    1.37
    F
    1.26
    Z
    1.17
    {
    1.16
    R
    1.15
    O
    1.15
    b
    1.14
    X
    1.12
    K
    1.11
    Activations Density 0.000%

    No Known Activations