© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127597
    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_3_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
     be
    0.80
    be
    0.80
    was
    0.64
    n
    0.64
     προσ
    0.63
    uh
    0.59
    ют
    0.59
    this
    0.59
    樟
    0.58
    icals
    0.57
    POSITIVE LOGITS
    ا۔
    0.73
    पाकिस्तान
    0.72
    。\
    0.71
     on
    0.71
    ری
    0.70
    ியது
    0.69
    다
    0.68
    اک
    0.66
     exclude
    0.63
    "
    0.62
    Activations Density 0.000%

    No Known Activations