© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236923
    Prev
    Next
    INDEX
    Explanations

    already been

    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
     remained
    0.39
    ازت
    0.38
    了起来
    0.37
     concisely
    0.37
     '**
    0.36
     explored
    0.35
    FactoryBean
    0.35
     debated
    0.34
    astava
    0.34
    졌
    0.34
    POSITIVE LOGITS
     உண்டா
    0.39
     producen
    0.37
    charm
    0.37
     être
    0.36
     transforms
    0.36
     gets
    0.35
     prides
    0.35
    כול
    0.35
     tratan
    0.35
     maîtres
    0.35
    Activations Density 0.002%

    No Known Activations