© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127235
    Prev
    Next
    INDEX
    Explanations

    quantifies periods or locations

    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_3_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
    N
    1.10
    S
    1.00
    L
    0.99
    W
    0.98
    C
    0.94
    K
    0.94
    M
    0.93
    D
    0.89
    R
    0.87
    B
    0.87
    POSITIVE LOGITS
     in
    0.69
     persists
    0.68
     determinants
    0.59
     אפ
    0.59
    িগ্ন
    0.59
     are
    0.57
     bilangan
    0.56
     fits
    0.56
     individuales
    0.56
     тур
    0.55
    Activations Density 0.000%

    No Known Activations