© 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. 5593
    Prev
    Next
    INDEX
    Explanations

    numerical digits and the apostrophe "'" character

    oai_token-act-pair · gemini-2.0-flash

    Code and numbers

    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
    Referències
    -0.56
    ValueStyle
    -0.53
    merking
    -0.48
     ProtoMessage
    -0.47
    EndContext
    -0.47
     tors
    -0.45
    TintMode
    -0.45
    ">//
    -0.43
    DeleteBehavior
    -0.43
     Ciro
    -0.42
    POSITIVE LOGITS
    photobucket
    0.55
    zość
    0.55
    voegen
    0.55
    يكب
    0.54
     root
    0.54
     ISTAT
    0.50
    doria
    0.49
    remoto
    0.49
     Sentences
    0.49
     mauvaises
    0.48
    Activations Density 0.103%

    No Known Activations