© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122628
    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_3_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
    ん
    0.67
    н
    0.66
    ut
    0.64
    ir
    0.64
    ing
    0.60
    ishing
    0.59
    ुलिस
    0.57
     denomin
    0.57
    ान
    0.56
    volving
    0.56
    POSITIVE LOGITS
    أ
    0.77
    I
    0.77
     ")
    0.75
     ')
    0.72
    9
    0.72
    )=\
    0.70
     douce
    0.70
    )
    0.70
    ことも
    0.69
    (
    0.69
    Activations Density 0.000%

    No Known Activations