© 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. 13707
    Prev
    Next
    INDEX
    Explanations

    the letter 'j' possibly surrounded by text like it would be in software code or equations

    oai_token-act-pair · gemini-2.0-flash

    sequences of the letter 'j'

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

    j

    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
    BagLayout
    -0.51
    ak
    -0.49
     CURIAM
    -0.49
     nakalista
    -0.49
    ंदीखरीदारी
    -0.47
    interopRequire
    -0.46
    TagMode
    -0.46
     SwiftUI
    -0.46
    AlterField
    -0.45
     Cualquier
    -0.45
    POSITIVE LOGITS
     հղումներ
    0.52
    gj
    0.52
    soort
    0.52
    atoes
    0.50
    AttributeSet
    0.50
    stwo
    0.50
     transférez
    0.50
    рс
    0.50
    ptonshire
    0.49
    runApp
    0.49
    Activations Density 0.848%

    No Known Activations