© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12160
    Prev
    Next
    INDEX
    Explanations

    the word "appeal"

    oai_token-act-pair · gemini-2.0-flash

    appeal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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>
    -0.96
     appeal
    -0.79
    twimg
    -0.72
     <=",
    -0.68
     autorytatywna
    -0.68
    HideFlags
    -0.66
     defaultstate
    -0.60
     Appeal
    -0.59
     APPEAL
    -0.59
    styleable
    -0.58
    POSITIVE LOGITS
     Preheat
    0.54
    esgue
    0.52
    Preheat
    0.52
     precept
    0.52
    actionMode
    0.51
     Prehistoric
    0.50
     moschino
    0.50
    RenderAtEndOf
    0.49
    raborty
    0.49
     Ditto
    0.48
    Activations Density 0.551%

    No Known Activations