© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1437
    Prev
    Next
    INDEX
    Explanations

    articles, determiners and adjectives that modify nouns

    oai_token-act-pair · gemini-2.0-flash

    The article "A"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '\\;'
    -0.71
     few
    -0.68
    LookAnd
    -0.67
    ]")]
    -0.67
    الحياه
    -0.66
    Few
    -0.66
     Few
    -0.63
    ReusableCell
    -0.63
    mặt
    -0.63
     ProtoMessage
    -0.63
    POSITIVE LOGITS
    нием
    0.50
     Inc
    0.48
    am
    0.47
     attorney
    0.47
     editor
    0.46
    ings
    0.46
     award
    0.46
     associate
    0.45
    cht
    0.45
    mac
    0.44
    Activations Density 2.307%

    No Known Activations