© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4717
    Prev
    Next
    INDEX
    Explanations

    grammatical structures, or sentences that use specific grammatical elements

    oai_token-act-pair · gemini-2.0-flash

    technical language or code terms

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

    Situation

    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
    KommentareTeilen
    -0.82
    XmlAccessorType
    -0.74
     ModelExpression
    -0.71
    InputBorder
    -0.71
    awakeFromNib
    -0.69
    GEBURTS
    -0.67
     referenties
    -0.66
     Mep
    -0.65
     Comprometido
    -0.64
    addCriterion
    -0.63
    POSITIVE LOGITS
     add
    0.48
    ByPrimaryKey
    0.48
    findpost
    0.45
     Cap
    0.45
    BeforeMethod
    0.45
     id
    0.43
    tokenize
    0.42
    gänge
    0.42
     Re
    0.42
    الج
    0.42
    Activations Density 0.396%

    No Known Activations