© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245698
    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_40_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
    igraphic
    0.39
     Gip
    0.39
     Rivera
    0.38
    יית
    0.37
    ratie
    0.37
    Footer
    0.36
     DiCaprio
    0.36
    爪
    0.36
    ritic
    0.35
    Atlantic
    0.35
    POSITIVE LOGITS
     engines
    0.48
     engine
    0.46
    エンジン
    0.42
    engine
    0.42
     ENGINE
    0.42
     ইঞ্জিন
    0.42
     엔진
    0.41
    发动机
    0.41
    enek
    0.39
     MNR
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.