© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2715
    Prev
    Next
    INDEX
    Explanations

    scientific and medical instruments, measurements, and procedures

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or data structures

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

    Scientific texts

    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
     Paar
    -0.53
    essen
    -0.49
    bye
    -0.48
    ader
    -0.48
     Bap
    -0.47
    hete
    -0.47
     getById
    -0.46
    MENAFN
    -0.45
     Tumors
    -0.44
     nargin
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.82
     ویکی‌پدی
    0.78
    abestanden
    0.66
    verwijspagina
    0.65
    transQ
    0.63
    SharedCtor
    0.63
    oredCriteria
    0.60
    omitempty
    0.59
    DebuggerNonUser
    0.59
    TypedDataSet
    0.58
    Activations Density 1.766%

    No Known Activations