© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8738
    Prev
    Next
    INDEX
    Explanations

    the word "says" or "said"

    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_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.85
    出版年
    -0.84
    ConstraintMaker
    -0.80
    ########.
    -0.76
    */),
    -0.73
    IntoConstraints
    -0.70
    bootstrapcdn
    -0.69
    AndEndTag
    -0.69
     Мексичка
    -0.68
     يتيمه
    -0.66
    POSITIVE LOGITS
     bevor
    0.36
    zają
    0.35
    paigns
    0.35
     RouterModule
    0.33
     remarquer
    0.33
    rety
    0.33
    fetchone
    0.33
     Volkes
    0.33
     Aplica
    0.32
    থ্য
    0.31
    Activations Density 0.075%

    No Known Activations