© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9948
    Prev
    Next
    INDEX
    Explanations

    blocks of consecutive numbers, punctuation, and certain adjectives

    oai_token-act-pair · gemini-2.0-flash

    identifiers or tags

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

    coding documentation

    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
     admissible
    -0.43
    Ljava
    -0.42
    tivo
    -0.41
    Reentrant
    -0.41
    ides
    -0.41
     допусти
    -0.41
    зви
    -0.40
    items
    -0.40
    ito
    -0.40
     UVA
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.93
    Datuak
    0.87
     Wikimedijinoj
    0.79
    MessageTagHelper
    0.75
    findpost
    0.75
     beginnetje
    0.69
    Diwedd
    0.68
    enumi
    0.67
    ViewImports
    0.66
    +#+#
    0.65
    Activations Density 1.013%

    No Known Activations