© 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. 9124
    Prev
    Next
    INDEX
    Explanations

    the word "information" and words associated with data analysis

    oai_token-act-pair · gemini-2.0-flash

    technical terminology related to information systems

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

    information

    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
     initComponents
    -0.50
     Makefile
    -0.49
    แห่ง
    -0.48
     Lib
    -0.46
    icher
    -0.45
    المكان
    -0.44
    enumi
    -0.44
    īgā
    -0.44
    ან
    -0.44
     précie
    -0.43
    POSITIVE LOGITS
    belea
    0.69
    EditorBrowsable
    0.68
     autorytatywna
    0.65
    BeginInit
    0.62
    GeneratedValue
    0.60
     getchar
    0.60
    errHandler
    0.58
    @[+][
    0.57
    Билгалдахарш
    0.56
     onCreateView
    0.56
    Activations Density 3.915%

    No Known Activations