© 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. 636
    Prev
    Next
    INDEX
    Explanations

    technical language used to describe scientific experiment methodology and results

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     lot
    -0.56
    Życiorys
    -0.53
     ton
    -0.50
     skills
    -0.49
     benefits
    -0.49
     Fuels
    -0.49
    oton
    -0.47
    TypedDataSet
    -0.46
     services
    -0.46
     strengths
    -0.45
    POSITIVE LOGITS
    Jeografia
    0.61
    -
    0.57
    rierten
    0.56
    A
    0.53
     hjemme
    0.50
     estrenar
    0.49
    zarchiwizowane
    0.48
    Kind
    0.48
     rodea
    0.48
    AV
    0.47
    Activations Density 16.696%

    No Known Activations