© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199353
    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_9_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
    ﻥ
    0.48
     Makarna
    0.48
    畊
    0.47
    တဲ့
    0.46
     Rew
    0.45
     Ngf
    0.45
    ﺔ
    0.44
    驾驶
    0.44
    鑣
    0.43
     Wills
    0.43
    POSITIVE LOGITS
    ρος
    0.46
    мос
    0.45
    телни
    0.43
    нис
    0.42
    хова
    0.42
    Pane
    0.42
    рес
    0.42
     말미암아
    0.41
    munition
    0.41
    ристо
    0.41
    Activations Density 0.000%

    No Known Activations