© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53189
    Prev
    Next
    INDEX
    Explanations

    regions and origins

    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_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
     gravely
    0.34
    ედა
    0.33
     ELEMENTS
    0.33
    renal
    0.32
     Acids
    0.32
     خاک
    0.31
     Sprache
    0.31
    覇
    0.31
     엄청
    0.30
     자랑
    0.30
    POSITIVE LOGITS
    BUUID
    0.34
     stained
    0.32
    istance
    0.32
     امریکا
    0.32
     south
    0.31
     Portugal
    0.31
     Argentina
    0.31
     Peru
    0.31
    انى
    0.31
     বগু
    0.31
    Activations Density 0.022%

    No Known Activations