© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92278
    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_60_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
    itt
    0.51
    ↵↵
    0.49
    -
    0.48
    AB
    0.47
    ABA
    0.46
    isto
    0.45
    data
    0.45
    aps
    0.45
    aba
    0.42
    ittee
    0.42
    POSITIVE LOGITS
     alguns
    0.43
     aumentar
    0.41
     några
    0.40
     enkele
    0.39
     epinephrine
    0.39
     unele
    0.38
    Ө
    0.38
    𝘮
    0.38
     disminuir
    0.38
     coltiv
    0.38
    Activations Density 0.000%

    No Known Activations