© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3421
    Prev
    Next
    INDEX
    Explanations

    terms related to chemistry, biology, fuels and their processes

    oai_token-act-pair · gemini-2.0-flash

    Utilizing/digesting compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     فريبيس
    -0.79
    mortar
    -0.54
    setViewportView
    -0.52
    encodeWith
    -0.52
    Nuorodos
    -0.50
     ourselves
    -0.47
     AssemblyTitle
    -0.47
    nalpot
    -0.46
    ATHY
    -0.46
    gyar
    -0.46
    POSITIVE LOGITS
    rrggbb
    0.68
     mergeFrom
    0.61
    AnchorStyles
    0.57
     typelib
    0.56
     оригіналу
    0.53
    SequentialGroup
    0.52
     parseFrom
    0.52
    ngOn
    0.51
    gole
    0.49
    didSet
    0.49
    Activations Density 2.399%

    No Known Activations