© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98848
    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_14_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
    v
    0.54
    *
    0.53
    ll
    0.51
     crear
    0.51
    W
    0.51
    Subscriber
    0.48
    C
    0.48
    tr
    0.47
     Spouse
    0.47
    và
    0.47
    POSITIVE LOGITS
     chestnuts
    0.55
     interspersed
    0.52
     cursing
    0.51
    ッティング
    0.51
     peduncul
    0.50
     Quel
    0.49
     pessimistic
    0.49
     pretentious
    0.49
     chromedp
    0.48
    _'.$
    0.48
    Activations Density 0.000%

    No Known Activations