© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13893
    Prev
    Next
    INDEX
    Explanations

    sentences containing certain common words/articles or is used to show progression of an idea or event

    oai_token-act-pair · gemini-2.0-flash

    is

    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
     magnum
    -0.40
     kole
    -0.40
    -"
    -0.40
    -“
    -0.39
    fasterxml
    -0.39
    Hentet
    -0.38
    ukin
    -0.38
    fn
    -0.36
    )};
    -0.36
     Mehl
    -0.36
    POSITIVE LOGITS
    PreferredItem
    0.77
    +#+
    0.77
    verwijspagina
    0.74
    expandindo
    0.69
    ngdoc
    0.66
     lenker
    0.65
    openqa
    0.64
    alnız
    0.63
     volontaire
    0.63
    protoc
    0.62
    Activations Density 0.706%

    No Known Activations