© 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. 24622
    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
    醤
    0.55
    Ꮙ
    0.52
    伈
    0.51
     특정
    0.50
     postseason
    0.49
     odmah
    0.49
     enfo
    0.48
     основных
    0.47
    芑
    0.46
     parametros
    0.46
    POSITIVE LOGITS
    2
    0.61
    off
    0.54
    ere
    0.52
    aff
    0.52
    of
    0.51
    room
    0.49
    plus
    0.49
    ade
    0.49
    ie
    0.47
    PR
    0.47
    Activations Density 0.000%

    No Known Activations