© 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. 5940
    Prev
    Next
    INDEX
    Explanations

    mostly blank lines or lines with very few characters

    oai_token-act-pair · gemini-2.0-flash

    code/data

    np_max-act · gemini-2.0-flash

    whitespace

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    …
    -0.68
    pon
    -0.55
    <bos>
    -0.54
    /
    -0.54
     and
    -0.54
    till
    -0.52
    ’
    -0.52
     is
    -0.51
    ten
    -0.49
    EOUT
    -0.49
    POSITIVE LOGITS
    expandindo
    1.34
     CreateTagHelper
    1.09
    RenderAtEndOf
    1.09
     كومونز
    1.09
    migrationBuilder
    1.07
     EconPapers
    1.06
     дописавши
    1.05
    ########.
    1.04
     Italij
    1.02
    Personensuche
    1.00
    Activations Density 0.700%

    No Known Activations