© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2412
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a change of state or going somewhere

    oai_token-act-pair · gemini-2.0-flash

    movement or change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ChartData
    -0.46
    =${
    -0.45
    Simplicity
    -0.45
    })));
    -0.45
    ]='\
    -0.44
    caya
    -0.43
    AntiForgeryToken
    -0.43
    ':{
    -0.43
    miso
    -0.42
    /${
    -0.42
    POSITIVE LOGITS
     our
    1.00
    我们的
    0.75
    our
    0.74
    我們的
    0.74
    Our
    0.73
    ніципалі
    0.73
     Our
    0.69
     we
    0.67
     الحره
    0.66
     unsere
    0.65
    Activations Density 6.631%

    No Known Activations