© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139723
    Prev
    Next
    INDEX
    Explanations

    AI models and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    pinephrine
    0.45
     Acceleration
    0.42
    \}^{
    0.40
     compactness
    0.39
     Preference
    0.39
    Acceleration
    0.38
     MP
    0.38
     AC
    0.37
    inositol
    0.37
     lacinia
    0.37
    POSITIVE LOGITS
     Siberia
    0.41
     Sloane
    0.40
    ඕ
    0.39
    irts
    0.38
     đậm
    0.38
    ely
    0.38
    柟
    0.38
    gten
    0.38
     dint
    0.38
    deadline
    0.37
    Activations Density 0.009%

    No Known Activations