© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9655
    Prev
    Next
    INDEX
    Explanations

    words related to legal and scientific texts, often with numbers.

    oai_token-act-pair · gemini-2.0-flash

    Technical/Legal/Scientific Texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     beginnetje
    -0.94
     CreateTagHelper
    -0.91
    TypedDataSet
    -0.83
     EconPapers
    -0.79
    AnchorStyles
    -0.71
    Autoritní
    -0.68
    évaluateur
    -0.68
     Савезне
    -0.68
    featureID
    -0.66
    matchCondition
    -0.65
    POSITIVE LOGITS
    rawValue
    0.48
     massive
    0.48
     raw
    0.46
     huge
    0.44
     Fe
    0.43
     total
    0.43
     locally
    0.42
    eleste
    0.42
     Massive
    0.42
    ÉS
    0.41
    Activations Density 7.897%

    No Known Activations