© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8137
    Prev
    Next
    INDEX
    Explanations

    phrases describing events, objects or properties and including coordinating words like "and" or "or", and/or punctuation like commas and parentheses

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
     (
    -0.46
    Chúng
    -0.40
    帖最后由
    -0.36
     indeed
    -0.34
    ,
    -0.34
    (
    -0.34
    éreo
    -0.34
    뀐
    -0.33
     revanche
    -0.33
    But
    -0.31
    POSITIVE LOGITS
     незавершена
    0.87
    StoryboardSegue
    0.78
    expandindo
    0.75
     لينك
    0.72
    rungsseite
    0.71
    دانشنامهٔ
    0.70
    Referències
    0.69
     jLabel
    0.69
    TargetException
    0.68
    WriteBarrier
    0.68
    Activations Density 5.875%

    No Known Activations