© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51215
    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_31_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
     سافٹ
    0.38
     어떻
    0.38
     compd
    0.37
    ᱐
    0.37
     হোমিও
    0.36
     superflu
    0.36
    锗
    0.36
     buckwheat
    0.35
     प्योर
    0.35
    ဝ
    0.35
    POSITIVE LOGITS
    countplot
    0.39
    arti
    0.38
    mug
    0.38
    calcul
    0.38
     आज
    0.37
    tsi
    0.36
    endio
    0.36
    fei
    0.35
    ha
    0.35
    adden
    0.35
    Activations Density 0.000%

    No Known Activations