© 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. 15734
    Prev
    Next
    INDEX
    Explanations

    the word "components", sometimes with a weak activation of nearby related terms

    oai_token-act-pair · gemini-2.0-flash

    components

    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
     kvinder
    -0.67
     økonom
    -0.65
    enumii
    -0.63
    utnik
    -0.60
     befolk
    -0.55
     klubben
    -0.52
     rivista
    -0.52
     overras
    -0.52
     iconst
    -0.52
     wikipagina
    -0.52
    POSITIVE LOGITS
    //};
    0.83
    iedene
    0.71
    gema
    0.67
    μβρίου
    0.65
     שוליים
    0.64
     Efq
    0.63
    interopRequire
    0.62
    usermodel
    0.61
    yce
    0.61
    };*/
    0.61
    Activations Density 3.379%

    No Known Activations