© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13744
    Prev
    Next
    INDEX
    Explanations

    sentences that contain numbers and dollar signs

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Filmographie
    -0.74
    ReusableCell
    -0.66
    Referências
    -0.63
    timewa
    -0.62
    balleur
    -0.61
    entee
    -0.61
    Hentet
    -0.58
    InputBorder
    -0.57
     typelib
    -0.54
    Bibliographie
    -0.54
    POSITIVE LOGITS
     gratuites
    0.56
     umano
    0.56
     ErrIntOverflow
    0.52
    WebElementEntity
    0.49
    havior
    0.48
    ukkig
    0.47
     umana
    0.47
    uskas
    0.47
     XNUMX
    0.44
     Anexo
    0.44
    Activations Density 0.875%

    No Known Activations