© 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. 15188
    Prev
    Next
    INDEX
    Explanations

    words and prefixes with hyphens.

    oai_token-act-pair · 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
     prayed
    -0.75
     cautioned
    -0.69
     sniffed
    -0.69
     voted
    -0.68
     drafted
    -0.68
     preached
    -0.65
     tarko
    -0.65
     turned
    -0.65
     competed
    -0.65
     souligne
    -0.65
    POSITIVE LOGITS
    Portail
    0.54
    WebElementEntity
    0.51
     web
    0.45
     TV
    0.44
    OrEmpty
    0.43
     list
    0.42
     Life
    0.42
    vanced
    0.42
    ########.
    0.42
    vermögen
    0.42
    Activations Density 6.810%

    No Known Activations