© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9216
    Prev
    Next
    INDEX
    Explanations

    titles of articles and other structural elements introducing text in a document

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming jargon

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     according
    -0.50
    ------
    -0.49
    cun
    -0.47
    ほうがいい
    -0.46
    emen
    -0.44
    intahan
    -0.44
     Sched
    -0.44
    -----
    -0.43
    Dorf
    -0.43
    方がいい
    -0.43
    POSITIVE LOGITS
    UnknownFields
    0.85
    AddTagHelper
    0.83
    mbggenerated
    0.69
    CodedInputStream
    0.66
    Външни
    0.66
    جغرافيا
    0.65
     jsPsych
    0.61
    sizeCache
    0.61
    tagHelperRunner
    0.60
     تكبرها
    0.60
    Activations Density 2.405%

    No Known Activations