© 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. 12759
    Prev
    Next
    INDEX
    Explanations

    language and keywords used on blogs, especially crafting blogs

    oai_token-act-pair · gemini-2.0-flash

    arts and crafts

    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
     craft
    -2.55
     Craft
    -2.52
    Craft
    -2.38
    craft
    -2.20
     crafts
    -2.16
    crafts
    -2.03
     Crafts
    -2.02
    CRAFT
    -2.02
    Crafts
    -1.95
     crafting
    -1.68
    POSITIVE LOGITS
     Paglinawan
    0.50
    ⎩
    0.50
     disk
    0.47
    מבר
    0.45
    FirebaseDatabase
    0.44
     [{
    0.44
     Bloomfield
    0.43
    >');
    0.42
    ginas
    0.42
     gyrus
    0.42
    Activations Density 1.344%

    No Known Activations