© 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. 10725
    Prev
    Next
    INDEX
    Explanations

    adjectives describing physical objects and their appearance.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'line'

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

    lines

    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
    fromnode
    -0.55
     "..\..\
    -0.50
     couvert
    -0.49
     Drapeau
    -0.48
     كومونز
    -0.48
     vinci
    -0.47
     Leith
    -0.47
    intios
    -0.46
     Holi
    -0.46
    vict
    -0.45
    POSITIVE LOGITS
     lines
    0.95
    lines
    0.84
     Lines
    0.73
     line
    0.72
    elines
    0.69
     parallel
    0.67
     angles
    0.66
     linhas
    0.66
     lignes
    0.66
    Lines
    0.65
    Activations Density 2.465%

    No Known Activations