© 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. 246185
    Prev
    Next
    INDEX
    Explanations

    file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ாகும்
    0.39
     Planung
    0.38
    䒿
    0.38
    δει
    0.37
     Pedagog
    0.37
     خودم
    0.36
     அலு
    0.36
    ığım
    0.36
    Liability
    0.36
     מג
    0.35
    POSITIVE LOGITS
    resolve
    0.41
     risol
    0.40
    ris
    0.39
    resolved
    0.39
    숍
    0.37
    ovol
    0.37
    
    0.37
    absolute
    0.36
    nika
    0.36
     கரை
    0.36
    Activations Density 0.000%

    No Known Activations