© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9528
    Prev
    Next
    INDEX
    Explanations

    variable names

    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_13_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
    u
    0.38
     اطلاع
    0.37
    count
    0.37
    urek
    0.35
    eleg
    0.35
    aur
    0.35
     देऊ
    0.35
    al
    0.34
    aug
    0.34
    .[[
    0.33
    POSITIVE LOGITS
    θη
    0.38
    ="
    0.37
     snow
    0.37
    </h3>
    0.36
     instrumentality
    0.35
     스
    0.34
     android
    0.34
     bloody
    0.34
     পদ্ধতি
    0.33
     pups
    0.33
    Activations Density 0.007%

    No Known Activations