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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6105
    Prev
    Next
    INDEX
    Explanations

    the ends of sentences and clauses

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'reach'

    np_token-act-pair-logits · gpt-4o-mini

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SBATCH
    -0.59
    MemoryWarning
    -0.57
    fhir
    -0.55
    
    -0.48
     Réponses
    -0.48
     referenties
    -0.48
     Follows
    -0.47
     volgens
    -0.46
    PostInfinity
    -0.45
    resizingMask
    -0.45
    POSITIVE LOGITS
     reach
    0.92
     Reach
    0.84
     reaching
    0.84
    Reach
    0.81
     reached
    0.77
     reaches
    0.76
    reach
    0.75
    queryInterface
    0.70
    reached
    0.70
     talk
    0.66
    Activations Density 2.009%

    No Known Activations