Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6850
    Prev
    Next
    INDEX
    Explanations

    colons preceded by a "said" verb or a noun

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ArgumentParser
    -0.64
    numerusform
    -0.59
    ReusableCell
    -0.57
    mtd
    -0.56
    WireFormat
    -0.53
     MainAxisSize
    -0.53
    amse
    -0.51
    arr
    -0.49
     Vorte
    -0.49
     Dedicated
    -0.48
    POSITIVE LOGITS
    httphttps
    0.57
    gorithm
    0.53
    ГЛА
    0.52
    BorderSize
    0.52
     lenker
    0.51
     LCCN
    0.50
    sleeping
    0.50
    trate
    0.49
     виправивши
    0.47
    INSEE
    0.47
    Activations Density 0.619%

    No Known Activations