© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82183
    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_0_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
     titulado
    0.49
    䳕
    0.48
     piè
    0.48
    করিয়
    0.47
     بأن
    0.46
    ।--
    0.46
     ابتد
    0.46
    ﭼ
    0.46
    ।-
    0.45
     বেকার
    0.45
    POSITIVE LOGITS
     a
    0.53
     have
    0.53
    OUT
    0.52
     autonomia
    0.50
    have
    0.50
    A
    0.50
     and
    0.49
    \
    0.49
    str
    0.47
    ste
    0.47
    Activations Density 0.000%

    No Known Activations