© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    mentions of graphing and functions

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "function"

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

    function

    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
     ostavi
    -0.73
    بوابة
    -0.59
     unknownFields
    -0.57
    ThroughAttribute
    -0.51
     continúas
    -0.51
     Mote
    -0.50
     мәкал
    -0.48
    CrossRef
    -0.48
     Commencez
    -0.48
     sẻ
    -0.47
    POSITIVE LOGITS
     function
    3.05
    function
    2.70
     functions
    2.53
     Function
    2.44
     Functions
    2.22
    Function
    2.20
     FUNCTION
    2.14
     fonction
    2.06
    functions
    2.06
     función
    2.02
    Activations Density 4.032%

    No Known Activations