© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223622
    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_10_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
    0.53
     exert
    0.48
     jitter
    0.46
     recreate
    0.45
    '
    0.45
     Have
    0.44
     produit
    0.44
    ﻨ
    0.44
     renovate
    0.43
     ເ
    0.43
    POSITIVE LOGITS
    outstanding
    0.53
    ug
    0.50
    Canonical
    0.49
    avic
    0.49
    ale
    0.48
    ozygous
    0.48
    utth
    0.48
    াতাড়ি
    0.48
    persistent
    0.47
    iten
    0.47
    Activations Density 0.000%

    No Known Activations