© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4706
    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_40_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
     लेते
    0.38
     Prendre
    0.38
    车
    0.38
     reciprocal
    0.37
    प्पू
    0.37
     अप
    0.37
     Growing
    0.37
    ახებ
    0.37
     nehmen
    0.36
    取
    0.36
    POSITIVE LOGITS
    ADI
    0.38
     TAD
    0.37
    突
    0.36
     dana
    0.34
     LY
    0.34
     deliveries
    0.34
     शिवाजी
    0.34
    UNI
    0.33
     ENEM
    0.33
     RES
    0.33
    Activations Density 0.018%

    No Known Activations