© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3662
    Prev
    Next
    INDEX
    Explanations

    content from scientific and technical documents that involves chemical composition and analysis

    oai_token-act-pair · gemini-2.0-flash

    chemical spectroscopy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    providedIn
    -0.89
    Rüyada
    -0.88
    +#+#
    -0.87
     désolés
    -0.87
    TagMode
    -0.81
     مرئيه
    -0.80
    Datuak
    -0.76
     propOrder
    -0.74
     Vikipedi
    -0.74
     ostavi
    -0.73
    POSITIVE LOGITS
    werk
    0.47
    aso
    0.44
    cy
    0.43
    ansk
    0.40
     mo
    0.39
    yad
    0.38
    ogram
    0.38
    SB
    0.38
    map
    0.37
    mius
    0.37
    Activations Density 0.774%

    No Known Activations