© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6311
    Prev
    Next
    INDEX
    Explanations

    words that indicate a connection or direction, literally or figuratively.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'lead'

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

    lead

    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
    IBarButtonItem
    -0.63
    setVerticalGroup
    -0.56
     CURIAM
    -0.55
    baguna
    -0.53
    GeneratedValue
    -0.52
    ureusement
    -0.52
     Karya
    -0.51
    orthand
    -0.51
    новниш
    -0.49
    ↹
    -0.49
    POSITIVE LOGITS
     lead
    2.53
     leads
    2.38
    lead
    2.27
     Lead
    2.19
    Lead
    2.11
    leads
    2.09
     Leads
    2.08
     leading
    2.06
     led
    1.98
     Leading
    1.95
    Activations Density 2.025%

    No Known Activations