© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28626
    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_10_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
     with
    0.56
     Expression
    0.52
     tarm
    0.51
    1
    0.47
     pemb
    0.47
     tarmac
    0.47
     to
    0.46
     GSi
    0.46
    2
    0.46
     whakap
    0.45
    POSITIVE LOGITS
    وري
    0.49
    幫助
    0.49
    aneus
    0.49
     تعريف
    0.48
    振り
    0.47
    adeo
    0.47
    tarea
    0.46
     ganado
    0.46
    ských
    0.46
    ંદ્ર
    0.46
    Activations Density 0.000%

    No Known Activations