© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204574
    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_37_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
    лове
    0.39
    绪
    0.38
     catchy
    0.37
     возраст
    0.37
    סטי
    0.36
     സ്ഥാപ
    0.36
    мато
    0.35
     teplot
    0.35
     pun
    0.35
    が高
    0.34
    POSITIVE LOGITS
    不敢
    0.40
     departure
    0.39
     _)
    0.38
    委
    0.38
     caballero
    0.37
     沈
    0.35
     출발
    0.35
     consult
    0.34
    ज्ञानिक
    0.34
     stems
    0.34
    Activations Density 0.000%

    No Known Activations