© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8969
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "or" as well as function words surrounding "or" and certain verbs.

    oai_token-act-pair · gemini-2.0-flash

    Non-English junk words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    more
    -2.63
    More
    -2.59
     More
    -2.56
     more
    -2.41
    MORE
    -2.38
     MORE
    -2.27
     mehr
    -1.88
    更多
    -1.66
     lebih
    -1.57
     más
    -1.55
    POSITIVE LOGITS
    expandindo
    0.66
    InSection
    0.56
    AutoScaleMode
    0.56
     Wikimedijinoj
    0.56
    ंदीखरीदारी
    0.54
     بتاريخ
    0.51
    osom
    0.47
     smallest
    0.47
    yship
    0.46
    ForType
    0.46
    Activations Density 9.471%

    No Known Activations