© 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. 10316
    Prev
    Next
    INDEX
    Explanations

    words relating to scientific research or studies

    oai_token-act-pair · gemini-2.0-flash

    without

    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
    alsa
    -0.39
    strtolower
    -0.38
    angolo
    -0.38
    elif
    -0.37
     mAdapter
    -0.36
    substring
    -0.36
    Slf
    -0.36
    ale
    -0.35
    HttpStatus
    -0.35
    inverse
    -0.35
    POSITIVE LOGITS
     without
    3.25
    without
    3.02
     Without
    2.98
    Without
    2.92
     WITHOUT
    2.59
    WITHOUT
    2.44
     zonder
    2.41
     senza
    2.34
     ohne
    2.34
     tanpa
    2.22
    Activations Density 4.416%

    No Known Activations