© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14009
    Prev
    Next
    INDEX
    Explanations

    the article "a" that is proceeded or followed by another article or a word related to authority, highness, or power

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     defaultstate
    -0.58
    enumi
    -0.56
    extérieur
    -0.55
     Wikimedijinoj
    -0.54
     QtWidgets
    -0.53
    Controllo
    -0.50
    égard
    -0.49
    culated
    -0.49
    número
    -0.49
    émission
    -0.48
    POSITIVE LOGITS
     alloy
    0.60
    apnews
    0.58
     error
    0.56
     anaerobic
    0.56
     income
    0.55
     exogenous
    0.54
     erreur
    0.53
     objet
    0.53
     IERC
    0.52
     altezza
    0.52
    Activations Density 1.281%

    No Known Activations