© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6339
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'rat' and words associated with biological or medical studies involving rats.

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to biological measurements

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

    Scientific study results

    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
     varandra
    -0.63
    참고
    -0.59
     autorytatywna
    -0.56
    بوابة
    -0.56
     morgon
    -0.53
     grève
    -0.52
    RetentionPolicy
    -0.49
     äldre
    -0.49
     viață
    -0.47
    <bos>
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.75
    AnchorStyles
    0.71
    findpost
    0.62
    afficheront
    0.61
    lorette
    0.58
    reh
    0.58
    useEffect
    0.55
    bata
    0.54
     mes
    0.54
    /**
    0.53
    Activations Density 2.726%

    No Known Activations