© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44878
    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_22_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
    সই
    0.44
     nutric
    0.43
    දන
    0.43
     }*/
    0.42
     Lakeside
    0.41
    簹
    0.41
    #![
    0.40
    يها
    0.39
    #$%
    0.39
    定番
    0.39
    POSITIVE LOGITS
    rap
    0.46
    Glue
    0.46
     lengkap
    0.45
     തയ്യാ
    0.44
     encapsulation
    0.42
    complete
    0.42
     reaction
    0.40
    rije
    0.40
     ra
    0.40
     화
    0.40
    Activations Density 0.000%

    No Known Activations