© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196594
    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_50_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
    .${
    0.41
     Personen
    0.39
    മ്പോൾ
    0.38
    <unused2231>
    0.38
     magnes
    0.37
    ﹎
    0.37
     বান্ধ
    0.36
    ={`
    0.35
    =${
    0.35
     accidens
    0.35
    POSITIVE LOGITS
    بوب
    0.48
     Blacks
    0.46
    ucine
    0.43
    astically
    0.42
    ustic
    0.41
     blacks
    0.39
    itas
    0.39
    bob
    0.39
     Gilbert
    0.38
    cust
    0.38
    Activations Density 0.000%

    No Known Activations