© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147734
    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_18_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
    清
    0.46
     admissibility
    0.44
     stoppage
    0.43
     labyrinth
    0.43
    </b>
    0.42
    </h4>
    0.42
     obstruction
    0.42
    首
    0.42
     amenity
    0.41
     alfabet
    0.41
    POSITIVE LOGITS
     הם
    0.49
     города
    0.49
     магазина
    0.49
    ಗ
    0.47
    Cola
    0.46
    INDU
    0.44
    рина
    0.44
     மட்டுமல்ல
    0.44
    Coca
    0.44
     શકો
    0.43
    Activations Density 0.000%

    No Known Activations