© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7080
    Prev
    Next
    INDEX
    Explanations

    examples and excerpts from source material

    oai_token-act-pair · gemini-2.0-flash

    taken from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    findpost
    -0.63
    kháu
    -0.59
    WriteBarrier
    -0.52
    GraphicsUnit
    -0.48
    WithTag
    -0.45
     stoneware
    -0.44
    buttonShape
    -0.44
    writeHead
    -0.44
     lccn
    -0.44
     ligiloj
    -0.43
    POSITIVE LOGITS
     taken
    1.68
    taken
    1.59
     from
    1.43
    Taken
    1.40
     Taken
    1.38
     extracted
    1.38
     TAKEN
    1.20
     borrowed
    1.15
    from
    1.14
    extracted
    1.13
    Activations Density 4.319%

    No Known Activations