© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129302
    Prev
    Next
    INDEX
    Explanations

    historical era

    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_1_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
     can
    1.16
     macroscopic
    1.01
     to
    0.98
     centros
    0.96
    ور
    0.94
    s
    0.92
     microsc
    0.90
     modulation
    0.90
     with
    0.89
     causality
    0.88
    POSITIVE LOGITS
    G
    1.81
    H
    1.80
    P
    1.79
    K
    1.72
    M
    1.67
    L
    1.60
    R
    1.57
    N
    1.53
    S
    1.50
    U
    1.48
    Activations Density 0.001%

    No Known Activations