© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202206
    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
    s
    1.20
    с
    1.19
    ों
    1.09
    ی
    1.02
    тих
    0.93
    し
    0.92
    ਆਂ
    0.91
    یی
    0.86
    skilled
    0.84
    ો
    0.83
    POSITIVE LOGITS
    na
    1.25
    나
    1.05
         
    0.95
    </strong>
    0.93
    in
    0.92
     DBMS
    0.92
     EHR
    0.91
    ना
    0.88
    ני
    0.88
     You
    0.86
    Activations Density 0.000%

    No Known Activations