© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13304
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    quels
    0.49
    t
    0.49
    segu
    0.48
    urgical
    0.48
    </h2>
    0.46
    on
    0.44
    友情
    0.44
    </u>
    0.44
    ap
    0.44
     Suicide
    0.44
    POSITIVE LOGITS
    ̀nh
    0.62
     yılı
    0.60
    ARON
    0.59
     vutto
    0.59
     stockno
    0.58
     yıll
    0.58
     thơ
    0.58
    Its
    0.57
     arquivo
    0.57
     yıl
    0.55
    Activations Density 0.000%

    No Known Activations