© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4432
    Prev
    Next
    INDEX
    Explanations

    mathematical or physics notation, especially with Greek letters and subscripts

    oai_token-act-pair · gemini-2.0-flash

    code/math

    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
    va
    -0.71
    v
    -0.70
    vā
    -0.70
    vá
    -0.69
    vas
    -0.68
    ve
    -0.67
    vu
    -0.67
    vin
    -0.66
    var
    -0.65
    ві
    -0.65
    POSITIVE LOGITS
     BoxFit
    0.50
    nu
    0.45
    AnchorStyles
    0.44
    Einsatz
    0.42
    HasAnnotation
    0.41
    antMatchers
    0.41
    actionMode
    0.41
    getColumnIndex
    0.41
    dike
    0.41
    CODES
    0.40
    Activations Density 2.855%

    No Known Activations