© 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. 8354
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    Spanish and French adjectives

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

    foreign words

    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
    writeFieldEnd
    -0.97
     EconPapers
    -0.92
    OGND
    -0.90
    webElementXpaths
    -0.88
    Билгалдахарш
    -0.85
    RenderAtEndOf
    -0.83
     transfieras
    -0.80
    ьаж
    -0.77
     صوتيه
    -0.77
     שוליים
    -0.75
    POSITIVE LOGITS
     domésticos
    0.49
     domestiques
    0.48
     aveug
    0.47
     colorés
    0.45
     administrativos
    0.43
     esclu
    0.42
     universale
    0.42
     laborales
    0.42
     legales
    0.42
     sauvages
    0.41
    Activations Density 4.729%

    No Known Activations