© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159138
    Prev
    Next
    INDEX
    Explanations

    in-depth

    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_2_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
    in
    1.86
    ו
    1.54
    F
    1.29
    o
    1.27
    et
    1.25
    N
    1.23
    m
    1.20
    V
    1.14
    u
    1.08
    𝐭
    1.07
    POSITIVE LOGITS
    ２
    1.23
    는
    1.22
    จะ
    1.08
    টি
    1.04
    OS
    1.03
     ۲
    1.02
    šao
    1.02
    ()=>{
    1.01
    2
    1.01
    and
    0.99
    Activations Density 0.004%

    No Known Activations