© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198359
    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_12_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
    _
    0.65
     cottages
    0.58
    εια
    0.57
     bungalows
    0.56
    น้ำ
    0.55
    घरों
    0.55
    rava
    0.54
     churches
    0.53
     nata
    0.53
    villa
    0.52
    POSITIVE LOGITS
     Bedien
    0.49
     B
    0.48
    やお
    0.47
     मर्द
    0.46
    必定
    0.46
    ك
    0.44
    criterion
    0.43
     Namely
    0.43
    solete
    0.43
     forcément
    0.43
    Activations Density 0.000%

    No Known Activations