© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10643
    Prev
    Next
    INDEX
    Explanations

    occurrences of common words like "the", "that", "this", and "is".

    oai_token-act-pair · gemini-2.0-flash

    This/That

    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
    GraphicsUnit
    -0.55
     bestaan
    -0.52
    >{@
    -0.47
    ※※
    -0.44
     gehouden
    -0.43
    andte
    -0.43
     PUBLICATIONS
    -0.42
    DropColumn
    -0.41
    ')(
    -0.40
    ínű
    -0.40
    POSITIVE LOGITS
     defaultstate
    0.82
    AnchorStyles
    0.70
    ⓘ
    0.68
     jScrollPane
    0.66
     urgency
    0.63
    multer
    0.63
     dryness
    0.63
     openness
    0.62
    serviceWorker
    0.61
     pretense
    0.61
    Activations Density 2.750%

    No Known Activations