© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11044
    Prev
    Next
    INDEX
    Explanations

    strings of characters used in JSON data

    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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tagHelperRunner
    -0.66
    تقاوى
    -0.63
    UpInside
    -0.62
    GraphicsUnit
    -0.62
    contentLoaded
    -0.60
    yntaxException
    -0.58
    reszcie
    -0.57
    ISupport
    -0.57
    NSIndexPath
    -0.56
    XMLSchema
    -0.56
    POSITIVE LOGITS
    EOUS
    0.54
    IENTE
    0.49
    IONAL
    0.49
     tartalomajánló
    0.47
     bordes
    0.46
    ientí
    0.46
     persil
    0.45
    cill
    0.44
    UnknownFields
    0.44
    guez
    0.44
    Activations Density 2.953%

    No Known Activations