© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7912
    Prev
    Next
    INDEX
    Explanations

    the word "genetic" and related words, sometimes with a small boost when they're used in the context of illness.

    oai_token-act-pair · gemini-2.0-flash

    genetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    I
    -0.63
    my
    -0.61
    this
    -0.60
     Se
    -0.56
    if
    -0.56
    i
    -0.55
    e
    -0.54
     satisfe
    -0.52
    g
    -0.52
     descomp
    -0.51
    POSITIVE LOGITS
     ―――――
    1.05
    etheless
    1.02
     \\
    0.98
    BibitemShut
    0.94
    $.
    0.93
     ſind
    0.93
    NUMX
    0.91
     ་་
    0.91
     iſt
    0.91
     whoſe
    0.91
    Activations Density 0.925%

    No Known Activations