© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155307
    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
    ції
    0.52
     For
    0.43
    رق
    0.42
    rů
    0.42
    𝗰
    0.42
    ів
    0.42
     omissions
    0.42
    дзі
    0.41
    এখানে
    0.41
     distinctions
    0.41
    POSITIVE LOGITS
    z
    0.53
    y
    0.49
    ZH
    0.47
    ilih
    0.46
     trúc
    0.45
    fim
    0.44
    bim
    0.44
    K
    0.44
    zame
    0.43
    zhen
    0.43
    Activations Density 0.000%

    No Known Activations