© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3163
    Prev
    Next
    INDEX
    Explanations

    text from academic papers about research studies

    oai_token-act-pair · gemini-2.0-flash

    collected

    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
     
    -0.50
     U
    -0.47
     I
    -0.44
     -
    -0.44
    .
    -0.42
     frame
    -0.42
     ch
    -0.40
     as
    -0.40
    <eos>
    -0.39
     N
    -0.39
    POSITIVE LOGITS
     Theſe
    0.92
     itſelf
    0.85
     متعلقه
    0.84
     disambiguazione
    0.84
     iNdEx
    0.82
     Efq
    0.82
     himſelf
    0.79
     ſhe
    0.79
    ChildScrollView
    0.79
     raiſ
    0.77
    Activations Density 27.835%

    No Known Activations