© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10050
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation and symbols

    oai_token-act-pair · gemini-2.0-flash

    prime symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tagext
    -0.82
    脚注の使い方
    -0.75
    ########.
    -0.73
    GeneratedCode
    -0.65
    __(/*!
    -0.65
    IntoConstraints
    -0.64
    StructEnd
    -0.63
     MainAxisSize
    -0.60
    Personendaten
    -0.59
    +#+
    -0.59
    POSITIVE LOGITS
     pol
    0.43
    Tog
    0.42
    ريكية
    0.41
    varia
    0.41
     hon
    0.40
    Това
    0.40
     pu
    0.40
    这款
    0.40
    참고
    0.39
     publisher
    0.39
    Activations Density 1.587%

    No Known Activations