© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2447
    Prev
    Next
    INDEX
    Explanations

    words related to dogs behavior and training

    oai_token-act-pair · gemini-2.0-flash

    BufferException

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     pstmt
    -0.56
    EXTERN
    -0.54
     feline
    -0.53
     délib
    -0.53
    Население
    -0.53
     Cat
    -0.51
     Veterinary
    -0.51
     Meow
    -0.51
     cat
    -0.51
     породы
    -0.50
    POSITIVE LOGITS
    BufferException
    0.68
    contentLoaded
    0.58
    Tembelea
    0.55
    simpleType
    0.54
    UIFont
    0.51
    //
    0.51
    BagConstraints
    0.50
     propOrder
    0.50
    setof
    0.49
    lně
    0.48
    Activations Density 27.267%

    No Known Activations