© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14003
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prove" and its variants

    oai_token-act-pair · gemini-2.0-flash

    Arguments and explanations

    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
     متحده
    -0.57
    UTC
    -0.56
     questão
    -0.54
     جغرافيا
    -0.52
     Sam
    -0.47
    </i>
    -0.47
     miss
    -0.47
     παρά
    -0.46
    прия
    -0.45
    Nazionale
    -0.45
    POSITIVE LOGITS
     Proof
    1.05
    Proof
    0.99
     proof
    0.98
     proofs
    0.97
     Proofs
    0.94
     proving
    0.94
     PROOF
    0.94
    Prove
    0.92
     proves
    0.91
     Prove
    0.90
    Activations Density 1.377%

    No Known Activations