© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3685
    Prev
    Next
    INDEX
    Explanations

    code snippets with parameter names and annotations

    oai_token-act-pair · gemini-2.0-flash

    code parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    diak
    -0.48
     namorado
    -0.47
     diverso
    -0.47
     diversa
    -0.46
     diferente
    -0.44
     partidos
    -0.43
     príncipe
    -0.43
     agricoles
    -0.43
     Klassen
    -0.43
    obar
    -0.42
    POSITIVE LOGITS
    <bos>
    1.76
    RectangleBorder
    0.88
    Geplaatst
    0.85
    UnusedPrivate
    0.82
     kasarigan
    0.81
    Datuak
    0.80
    Personensuche
    0.80
    StoryboardSegue
    0.77
    matchCondition
    0.77
    ArrowToggle
    0.75
    Activations Density 0.355%

    No Known Activations