© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11517
    Prev
    Next
    INDEX
    Explanations

    technical writing related to semiconductors, electricity, and physics

    oai_token-act-pair · gemini-2.0-flash

    electricity

    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
    formik
    -0.71
    ();*/
    -0.69
    lorette
    -0.67
     reticulum
    -0.66
    ']],
    -0.66
    '},
    -0.66
    rogels
    -0.66
    ')],
    -0.66
     Audiodateien
    -0.65
     kasarigan
    -0.65
    POSITIVE LOGITS
    <bos>
    0.66
    tagHelperRunner
    0.58
    protoimpl
    0.54
    unknownFields
    0.54
    SerializedName
    0.47
    isSet
    0.47
     spatio
    0.47
    liferay
    0.47
     Reverso
    0.46
    ніципа
    0.45
    Activations Density 6.283%

    No Known Activations