© 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. 10678
    Prev
    Next
    INDEX
    Explanations

    language appropriate to laws

    oai_token-act-pair · gemini-2.0-flash

    Legal/technical writing

    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
     par
    -0.47
     tiennent
    -0.45
    asikan
    -0.42
    nodoc
    -0.42
    politan
    -0.41
     merken
    -0.40
     bestätigen
    -0.40
    roveň
    -0.40
    nová
    -0.39
     inconvénients
    -0.39
    POSITIVE LOGITS
    المناصب
    0.89
     pinulongan
    0.70
     continuant
    0.69
     BioLib
    0.66
    Xna
    0.65
    apimachinery
    0.65
     narrowing
    0.63
    WriteBarrier
    0.63
     broadest
    0.61
    GraphicsUnit
    0.60
    Activations Density 1.635%

    No Known Activations