© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12242
    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
     triun
    0.39
     initComponents
    0.35
     retros
    0.34
     metá
    0.34
    <unused17>
    0.33
     frü
    0.33
     Catar
    0.33
    काया
    0.33
    <unused42>
    0.32
     Yun
    0.32
    POSITIVE LOGITS
    long
    0.44
     Flows
    0.42
     long
    0.39
    flows
    0.38
     허
    0.38
    documented
    0.37
     documented
    0.37
     Boundary
    0.37
     οδη
    0.37
     границ
    0.36
    Activations Density 0.014%

    No Known Activations