© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8881
    Prev
    Next
    INDEX
    Explanations

    the word "has" and forms of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ibatis
    -0.59
     <=",
    -0.56
    expiresIn
    -0.56
    webElementXpaths
    -0.55
    OTO
    -0.52
    Referințe
    -0.50
    osoba
    -0.49
    jws
    -0.49
    XtraReports
    -0.49
     sander
    -0.49
    POSITIVE LOGITS
    httphttps
    0.60
    Personensuche
    0.53
    رایط
    0.52
     olvides
    0.51
     насељу
    0.50
    tvguidetime
    0.50
     kän
    0.49
    何より
    0.49
     pitä
    0.49
     tramonto
    0.49
    Activations Density 0.964%

    No Known Activations