© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108287
    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_1_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
     in
    1.52
     can
    1.12
    r
    1.09
     as
    1.02
    e
    1.02
     。
    1.01
    在
    1.01
     في
    0.99
    c
    0.98
    يد
    0.97
    POSITIVE LOGITS
    на
    1.07
    써
    1.05
    ль
    1.05
    parametric
    1.04
    ι
    1.01
    ной
    0.99
    ل
    0.99
    ना
    0.98
    ங்க
    0.98
    た
    0.96
    Activations Density 0.000%

    No Known Activations