© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153414
    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
     It
    0.63
     Your
    0.63
     There
    0.59
     Its
    0.58
     Their
    0.57
     For
    0.57
     P
    0.55
     Uses
    0.54
     W
    0.54
     Playing
    0.54
    POSITIVE LOGITS
     profundo
    0.44
     corretamente
    0.44
    дных
    0.44
    racción
    0.43
     cercanos
    0.43
     rightfully
    0.43
     rapidement
    0.43
    дная
    0.41
    品质
    0.40
    рная
    0.40
    Activations Density 0.000%

    No Known Activations