© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15000
    Prev
    Next
    INDEX
    Explanations

    code documentation and class definitions

    oai_token-act-pair · gemini-2.0-flash

    parameters and properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.85
    ,
    -0.72
     in
    -0.64
     that
    -0.61
     as
    -0.60
     and
    -0.60
     he
    -0.56
     
    -0.55
     of
    -0.54
     at
    -0.54
    POSITIVE LOGITS
     Efq
    1.21
     Theſe
    1.16
     ujednoznacz
    1.12
     surla
    1.09
    GEBURTS
    1.04
    __':
    1.04
     Anſ
    0.99
    adecimal
    0.98
    NUMX
    0.96
     Monfieur
    0.95
    Activations Density 0.381%

    No Known Activations