© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9248
    Prev
    Next
    INDEX
    Explanations

    instances of the word "parameter" or "coefficient"

    oai_token-act-pair · gemini-2.0-flash

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     parameter
    -2.50
     Parameter
    -2.42
     parameters
    -2.42
     Parameters
    -2.36
    Parameter
    -2.25
    parameter
    -2.20
    Parameters
    -2.16
    parameters
    -2.13
     PARAMETERS
    -1.93
     PARAMETER
    -1.91
    POSITIVE LOGITS
     Inet
    0.56
    ynb
    0.53
    Facades
    0.52
     avsl
    0.50
     classNames
    0.49
    nthesis
    0.47
    classnames
    0.47
    MENAFN
    0.47
    jarah
    0.46
    Clima
    0.45
    Activations Density 0.749%

    No Known Activations