© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11927
    Prev
    Next
    INDEX
    Explanations

    technical words and names of people, places, and things.

    oai_token-act-pair · gemini-2.0-flash

    poorly formatted text

    np_max-act · gemini-2.0-flash

    word endings

    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
    othesis
    -1.73
    encils
    -1.73
    hematical
    -1.64
    tershire
    -1.58
    ividual
    -1.54
    nicity
    -1.53
    ipheral
    -1.49
    gnition
    -1.45
    ineſs
    -1.45
    ratulations
    -1.45
    POSITIVE LOGITS
    expandindo
    1.33
    +#+#
    1.32
    MigrationBuilder
    1.28
     kasarigan
    1.22
    RenderAtEndOf
    1.20
     '\\;'
    1.14
    Tikang
    1.10
    ValueStyle
    1.09
    #+#
    1.09
     متعلقه
    1.09
    Activations Density 13.108%

    No Known Activations