© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5858
    Prev
    Next
    INDEX
    Explanations

    the words "end", "up", "set", "started", or other related verbs.

    oai_token-act-pair · gemini-2.0-flash

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     automatiques
    -0.70
     chré
    -0.69
     scolaires
    -0.68
     hiér
    -0.68
     démocr
    -0.65
     énergé
    -0.65
     indépendante
    -0.65
     fidélité
    -0.61
     cérami
    -0.61
     aéreo
    -0.60
    POSITIVE LOGITS
     كومونز
    0.66
    
    0.61
    IntoConstraints
    0.55
     المعيارى
    0.54
    writeFieldEnd
    0.54
    MessageOf
    0.54
     paying
    0.52
     hers
    0.52
    ImageContext
    0.52
    parsedMessage
    0.51
    Activations Density 9.173%

    No Known Activations