© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12118
    Prev
    Next
    INDEX
    Explanations

    dialogue within quotations and people's thoughts about dialogue

    oai_token-act-pair · gemini-2.0-flash

    fantasy novel excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     NSCoder
    -0.62
    pulumi
    -0.61
    angliski
    -0.59
     CURIAM
    -0.58
    INCREF
    -0.58
     /*#__
    -0.57
    CITATION
    -0.57
    skjaer
    -0.55
     doigts
    -0.54
     fallu
    -0.54
    POSITIVE LOGITS
    <bos>
    0.96
     <>",
    0.54
    Życiorys
    0.54
     Italijanski
    0.54
    ValueStyle
    0.53
    SourceChecksum
    0.52
     GenerationType
    0.48
    I
    0.48
    Facades
    0.47
     мәкалә
    0.47
    Activations Density 1.724%

    No Known Activations