© 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. 3006
    Prev
    Next
    INDEX
    Explanations

    mentions of a group of things as one entity

    oai_token-act-pair · gemini-2.0-flash

    collections and descriptions

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

    groups of things

    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
    KommentareTeilen
    -0.53
     समीक्षाओं
    -0.50
    tran
    -0.47
    Rohy
    -0.47
    TestingModule
    -0.47
    DidLoad
    -0.46
    ienta
    -0.46
    ppard
    -0.45
    GGI
    -0.45
    «
    -0.44
    POSITIVE LOGITS
     of
    0.79
     containing
    0.73
     INCLUDING
    0.72
     ISNI
    0.71
     Containing
    0.70
     featuring
    0.69
     Featuring
    0.66
     innehåller
    0.64
    tagHelperRunner
    0.64
     depicting
    0.64
    Activations Density 5.669%

    No Known Activations