© 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. 7648
    Prev
    Next
    INDEX
    Explanations

    words related to creative or artistic endeavors, or specific types of media.

    oai_token-act-pair · gemini-2.0-flash

    creative works

    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
    addCriterion
    -0.41
    ़
    -0.40
     pseudo
    -0.38
     jScrollPane
    -0.38
     gar
    -0.37
    =“
    -0.37
    первых
    -0.37
     layui
    -0.36
     liquid
    -0.36
     urllib
    -0.36
    POSITIVE LOGITS
    FieldBuilder
    0.88
     Houſe
    0.77
    WithIOException
    0.73
     Efq
    0.73
    IsContent
    0.73
    ñora
    0.71
     Anſ
    0.68
     Majefty
    0.68
     Shakspeare
    0.68
     itſelf
    0.67
    Activations Density 11.049%

    No Known Activations