© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 208949
    Prev
    Next
    INDEX
    Explanations

    numbers followed by family or dependents

    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_20_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
     apabila
    0.31
    ak
    0.31
    ජ
    0.31
    yre
    0.30
     nếu
    0.29
    kkue
    0.29
     regista
    0.29
     የበ
    0.29
     jeśli
    0.29
    yto
    0.28
    POSITIVE LOGITS
     privately
    0.32
     い
    0.31
    Soci
    0.31
    πων
    0.29
    </em>
    0.29
    దని
    0.28
    MEs
    0.28
    
    0.28
     .)
    0.27
    それを
    0.27
    Activations Density 0.001%

    No Known Activations