© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132713
    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_6_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
     was
    1.19
    </h1>
    1.09
     et
    1.09
    ,
    1.09
     be
    1.05
    ,"
    1.03
    O
    0.99
     I
    0.98
    '
    0.97
    -
    0.93
    POSITIVE LOGITS
    ین
    1.21
    u
    1.17
    지
    1.16
    其他
    1.08
     múltipl
    1.07
    a
    1.05
    지에
    1.03
     смесь
    1.01
     інших
    1.00
    یل
    0.98
    Activations Density 0.000%

    No Known Activations