Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1638
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and some keywords after them (i.e. bits, bit, U.S.C, bit, bit, sec)

    oai_token-act-pair · gemini-2.0-flash

    6

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]];
    -0.52
     }</
    -0.51
    ++
    
    -0.50
    er
    -0.46
    ers
    -0.45
    ."));
    -0.45
    ()<<
    -0.44
    "},
    
    -0.43
    [];
    
    -0.42
    />";
    -0.41
    POSITIVE LOGITS
     виправивши
    1.08
    Hentet
    0.85
    Portale
    0.77
    webElementGuid
    0.77
     CiNii
    0.74
     calendriers
    0.72
     незавершена
    0.70
    PhysRevD
    0.70
     defStyleAttr
    0.69
     ferons
    0.68
    Activations Density 50.875%

    No Known Activations