© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3801
    Prev
    Next
    INDEX
    Explanations

    forms of the word "influence" and words associated with it such as significance, impartiality, basis, and consideration

    oai_token-act-pair · gemini-2.0-flash

    influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     suivants
    -0.76
    CrossRef
    -0.75
     larmes
    -0.74
     köl
    -0.73
     همچنین
    -0.73
     varandra
    -0.72
     rayures
    -0.71
    ambién
    -0.70
     jouets
    -0.70
     lèvres
    -0.69
    POSITIVE LOGITS
    ']))
    0.57
    mandu
    0.57
    Transkript
    0.56
     Prolog
    0.55
     damn
    0.54
    دانشنامهٔ
    0.54
     darn
    0.54
    )))
    0.54
    ing
    0.52
     Wikis
    0.51
    Activations Density 1.863%

    No Known Activations