© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14774
    Prev
    Next
    INDEX
    Explanations

    sections in legal, scientific, or technical documents labeled with roman or alphabetic enumerations

    oai_token-act-pair · gemini-2.0-flash

    Lists with roman numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     оригіналу
    -0.59
    يكب
    -0.56
    новниш
    -0.52
    inerie
    -0.52
    ścioła
    -0.49
     geschlagen
    -0.49
    BagLayout
    -0.48
     disponibilités
    -0.48
    brtc
    -0.48
    навли
    -0.48
    POSITIVE LOGITS
    findpost
    0.91
    +#+#
    0.71
    enumi
    0.63
     "..\..\..\
    0.60
     Chwiliwch
    0.57
     concentrated
    0.57
     TestBed
    0.56
    stateMutability
    0.55
     estekak
    0.52
    enumii
    0.52
    Activations Density 49.527%

    No Known Activations