© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199094
    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_9_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
    print
    0.54
    v
    0.54
    op
    0.53
    q
    0.53
    tal
    0.52
    test
    0.52
    an
    0.50
    man
    0.49
    P
    0.49
    travel
    0.49
    POSITIVE LOGITS
     izbor
    0.58
     odpowiedzi
    0.55
     seleccionar
    0.52
     exhort
    0.50
     zapis
    0.50
     contraste
    0.50
     szt
    0.49
     uczni
    0.49
    ควร
    0.49
     déput
    0.49
    Activations Density 0.000%

    No Known Activations