© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196494
    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_4_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
    s
    0.79
    ل
    0.68
     to
    0.63
     for
    0.63
     Add
    0.62
    ك
    0.61
    pos
    0.60
     of
    0.59
    new
    0.58
     Association
    0.58
    POSITIVE LOGITS
     compreensão
    0.57
    ̪
    0.55
     razão
    0.53
     circulación
    0.53
     அவர்களின்
    0.52
     fortaleza
    0.50
     detriment
    0.49
     profondément
    0.49
    arına
    0.48
     divaricatis
    0.48
    Activations Density 0.000%

    No Known Activations