© 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. 108038
    Prev
    Next
    INDEX
    Explanations

    dinosaur dig fossils lover

    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
    at
    1.20
    has
    1.16
    if
    1.06
    i
    1.05
    ل
    1.05
    v
    0.98
    ر
    0.94
     this
    0.93
     you
    0.92
    ro
    0.90
    POSITIVE LOGITS
    의
    1.09
    :
    1.06
    的
    1.02
    이자
    0.87
    é
    0.87
    ın
    0.84
    이지만
    0.80
    이란
    0.80
    𓂀
    0.80
    이었다
    0.79
    Activations Density 0.001%

    No Known Activations