© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10999
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "cap" or the first three letters of the word "capital"

    oai_token-act-pair · gemini-2.0-flash

    cap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    WebMethod
    -0.50
    UnifiedTopology
    -0.50
     micro
    -0.50
    ंत्री
    -0.48
    principalColumn
    -0.47
     Pyle
    -0.45
    ByExample
    -0.44
     Beatty
    -0.44
     kaynağından
    -0.43
    JpaRepository
    -0.43
    POSITIVE LOGITS
     ProtoMessage
    0.75
     <=",
    0.73
    parsedMessage
    0.72
     nakalista
    0.69
     OFDb
    0.66
    StoryboardSegue
    0.58
     Normdatei
    0.56
     متعلقه
    0.56
    verwijspagina
    0.54
    ofire
    0.54
    Activations Density 0.328%

    No Known Activations