© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12482
    Prev
    Next
    INDEX
    Explanations

    mentions of emotional desires and also of legal cases involving the last name "Se" and county "Nat"

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.54
     disambiguazione
    -0.48
    coun
    -0.46
     quorum
    -0.46
     Boucher
    -0.44
    ewoo
    -0.44
     CWE
    -0.42
     counsel
    -0.42
     putty
    -0.41
    RenderAtEndOf
    -0.41
    POSITIVE LOGITS
    FileInputStream
    0.65
     Biggs
    0.63
    AIN
    0.60
     isInitialized
    0.60
    Bism
    0.59
    WithIdentifier
    0.59
     lin
    0.58
    لیس
    0.57
    findById
    0.56
     Mitar
    0.56
    Activations Density 5.022%

    No Known Activations