© 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. 9216
    Prev
    Next
    INDEX
    Explanations

    the word "eat" and words related to eating habits

    oai_token-act-pair · gemini-2.0-flash

    eat

    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
     eat
    -2.55
     eating
    -2.25
     Eat
    -2.17
    Eat
    -2.13
     eats
    -2.08
    eat
    -2.05
     Eating
    -2.00
    eating
    -1.96
     eaten
    -1.96
     ate
    -1.96
    POSITIVE LOGITS
    évaluateur
    0.48
    oucí
    0.46
    guided
    0.46
     '%'
    0.45
    pters
    0.45
    pys
    0.44
    antaine
    0.43
     thereto
    0.43
     Verk
    0.43
     selv
    0.42
    Activations Density 0.998%

    No Known Activations