© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9135
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measure

    oai_token-act-pair · gemini-2.0-flash

    numerical values and measurements

    np_token-act-pair-logits · gpt-4o-mini

    Ratios and amounts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    PMailer
    -0.81
    OGND
    -0.79
     تضيفلها
    -0.74
    ftagPool
    -0.70
    BASEPATH
    -0.69
    rungsseite
    -0.69
    HasAnnotation
    -0.65
    esgue
    -0.64
     propOrder
    -0.64
     surla
    -0.63
    POSITIVE LOGITS
    LLocation
    0.47
     many
    0.47
     Many
    0.47
    x
    0.46
     phase
    0.46
    many
    0.46
    Y
    0.45
     events
    0.44
    Erreferentziak
    0.44
     frame
    0.44
    Activations Density 3.846%

    No Known Activations