© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3054
    Prev
    Next
    INDEX
    Explanations

    uses of the word "say" or "tell", especially when followed by a quote or pronoun.

    oai_token-act-pair · gemini-2.0-flash

    saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     للمعارف
    -0.88
     tartalomajánló
    -0.84
    OGND
    -0.71
     transfieras
    -0.71
    AddTagHelper
    -0.71
     Савезне
    -0.70
     gdyby
    -0.69
    SequentialGroup
    -0.67
     ivelany
    -0.67
    yntaxException
    -0.67
    POSITIVE LOGITS
    PEAT
    0.50
    usermodel
    0.49
    ReactDOM
    0.47
    ánea
    0.47
    مين
    0.43
     Kies
    0.43
    További
    0.43
    thin
    0.42
    advantage
    0.42
     gain
    0.42
    Activations Density 0.875%

    No Known Activations