© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10529
    Prev
    Next
    INDEX
    Explanations

    code related to 3D models

    oai_token-act-pair · gemini-2.0-flash

    Model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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>
    -1.11
    Model
    -1.07
     Model
    -0.82
    SourceChecksum
    -0.75
     Mal
    -0.57
     ja
    -0.54
     mal
    -0.54
     je
    -0.52
     gal
    -0.50
     effort
    -0.50
    POSITIVE LOGITS
     avoient
    0.68
     étoient
    0.67
    Portail
    0.61
     Bessel
    0.60
     Reſ
    0.58
     keines
    0.58
     neceſſ
    0.57
     Tourisme
    0.57
     Portail
    0.57
    thole
    0.56
    Activations Density 1.809%

    No Known Activations