© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11801
    Prev
    Next
    INDEX
    Explanations

    text comparing different numerical proportions, especially percentages

    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
     bird
    -2.34
     Bird
    -2.22
     birds
    -2.17
    Bird
    -2.09
     BIRD
    -2.06
     Birds
    -2.05
    bird
    -2.02
    Birds
    -1.91
    BIRD
    -1.86
    birds
    -1.84
    POSITIVE LOGITS
    Portale
    0.55
    stanz
    0.50
     Réunion
    0.50
    stanley
    0.48
    alnız
    0.48
    norsk
    0.48
     Joh
    0.48
    Joh
    0.47
     Tand
    0.46
    AsUp
    0.46
    Activations Density 0.660%

    No Known Activations