© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words in the context of telling someone's story

    oai_token-act-pair · gemini-2.0-flash

    Sensory perception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     provided
    -1.27
     Provided
    -1.17
    provided
    -1.12
     taught
    -1.04
     offered
    -1.02
     supplied
    -1.02
    Provided
    -0.99
     enabled
    -0.96
     facilitated
    -0.95
     brought
    -0.95
    POSITIVE LOGITS
     heard
    0.82
    Hochspringen
    0.75
    heard
    0.72
     overheard
    0.69
     learned
    0.62
     fell
    0.61
     missed
    0.60
     felt
    0.60
     gesehen
    0.60
    felt
    0.59
    Activations Density 4.137%

    No Known Activations