© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201018
    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
     vv
    0.40
     sanitation
    0.39
     @
    0.39
     encomendas
    0.37
    aminar
    0.37
    τια
    0.37
    asiun
    0.37
    acu
    0.36
    仿
    0.36
    樞
    0.36
    POSITIVE LOGITS
     weakens
    0.41
     separated
    0.40
     suggesting
    0.40
     продолжает
    0.40
     continúa
    0.39
     causando
    0.38
     suggests
    0.38
    understanding
    0.38
     व्यक्ति
    0.37
    িকায়
    0.37
    Activations Density 0.000%

    No Known Activations