© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    the phrase 'taking advantage' and some non-ASCII characters

    oai_token-act-pair · gemini-2.0-flash

    taking advantage

    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
    szönöm
    -0.60
    wijk
    -0.56
    Slf
    -0.56
     hva
    -0.54
    lück
    -0.54
    podar
    -0.52
    gamon
    -0.51
    ispiel
    -0.51
    APPLIC
    -0.50
     CURLOPT
    -0.50
    POSITIVE LOGITS
    ⓧ
    0.73
     تانيه
    0.65
     externi
    0.60
    <bos>
    0.58
     uska
    0.57
     صوتيه
    0.57
    حياتها
    0.57
    Datuak
    0.55
    modelBuilder
    0.54
    webElementXpaths
    0.54
    Activations Density 0.118%

    No Known Activations