© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3796
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    oai_token-act-pair · gemini-2.0-flash

    Code/data from software

    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
    */),
    -0.56
    unately
    -0.55
    ennium
    -0.52
    |,
    -0.46
    dération
    -0.45
    ฐาน
    -0.45
    접
    -0.45
    posure
    -0.44
    *",
    -0.43
    veau
    -0.43
    POSITIVE LOGITS
    ChildScrollView
    0.76
    Autoritní
    0.64
    DeleteBehavior
    0.59
    Diwedd
    0.59
    ConstraintMaker
    0.58
    AddTagHelper
    0.57
     jspb
    0.54
    
    0.54
     Walkover
    0.54
    TargetException
    0.53
    Activations Density 20.259%

    No Known Activations