© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12878
    Prev
    Next
    INDEX
    Explanations

    information about someone, including their title and where they live

    oai_token-act-pair · gemini-2.0-flash

    News article snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     iParam
    -0.48
    FormTagHelper
    -0.48
     stanovnika
    -0.48
    enumii
    -0.47
    Gdx
    -0.46
    Swatch
    -0.45
     <<<<<<<<<<<<<<
    -0.45
     éc
    -0.45
    ynchrotron
    -0.45
    ctiva
    -0.44
    POSITIVE LOGITS
     MainAxisSize
    0.80
     المعيارى
    0.60
    قایناق‌لار
    0.59
     Acerca
    0.59
    DialogContent
    0.57
    فاض
    0.55
    ']]
    0.54
    agisse
    0.54
    tagHelperRunner
    0.54
    DoubleQuotes
    0.53
    Activations Density 4.944%

    No Known Activations