© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11497
    Prev
    Next
    INDEX
    Explanations

    statistics and numbers related to sports

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     scale
    -1.02
     year
    -0.94
     level
    -0.88
     Scale
    -0.87
     hour
    -0.80
     length
    -0.74
     Year
    -0.72
     YEAR
    -0.72
     minute
    -0.72
     time
    -0.71
    POSITIVE LOGITS
    뀔
    0.61
    cokinetics
    0.59
    뀐
    0.57
    atilde
    0.55
    mtrl
    0.55
    عادة
    0.54
     recensement
    0.54
    urier
    0.54
    bilities
    0.54
    loài
    0.53
    Activations Density 3.613%

    No Known Activations