© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 872
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_44_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
    四大
    0.42
    aust
    0.41
    暖
    0.38
     warms
    0.36
    ୪
    0.36
    חר
    0.36
    Aust
    0.36
    ふわ
    0.35
     mih
    0.35
     warmed
    0.34
    POSITIVE LOGITS
    ৬০
    0.38
    agua
    0.38
     سائ
    0.38
    צוני
    0.38
    ৯০
    0.38
    ৩০
    0.36
    স্তক
    0.36
     ago
    0.35
     operación
    0.35
    싶
    0.35
    Activations Density 0.152%

    No Known Activations