© 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. 13486
    Prev
    Next
    INDEX
    Explanations

    proper nouns and numbers

    oai_token-act-pair · gemini-2.0-flash

    terms related to statistics and measurements

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

    Names

    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
    rungsseite
    -0.93
    TagMode
    -0.92
    SharedDtor
    -0.84
     disambiguazione
    -0.83
    ValueStyle
    -0.73
    DockStyle
    -0.72
     his
    -0.70
     propOrder
    -0.70
    Autoritní
    -0.68
    balleur
    -0.68
    POSITIVE LOGITS
     bonté
    0.56
    qtype
    0.45
     of
    0.45
     humeur
    0.44
    랜드
    0.44
    iros
    0.43
    ειτουργ
    0.43
     tarko
    0.43
     auttaa
    0.43
     keskus
    0.42
    Activations Density 3.385%

    No Known Activations