© 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. 7470
    Prev
    Next
    INDEX
    Explanations

    the word "flat" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    sequences starting with 'flat' or 'Flat'

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

    flat

    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
     समीक्षाओं
    -0.64
    AndEndTag
    -0.63
    AnchorTagHelper
    -0.62
     ***!
    -0.58
    Jeografia
    -0.57
    AnchorStyles
    -0.56
    Referències
    -0.55
     BytesLike
    -0.54
    LookAnd
    -0.54
    :✨
    -0.54
    POSITIVE LOGITS
    <>(
    0.54
    <>("
    0.52
     dám
    0.48
    viri
    0.47
    ened
    0.46
     ters
    0.46
     poser
    0.45
    رو
    0.45
    amir
    0.45
    eso
    0.44
    Activations Density 1.592%

    No Known Activations