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. 1582
    Prev
    Next
    INDEX
    Explanations

    information describing an artist, including the art they create, where they live, and their education

    oai_token-act-pair · gemini-2.0-flash

    artistic works

    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
     endforeach
    -0.54
    ьаж
    -0.50
     ProtoMessage
    -0.49
    Initializable
    -0.49
    }))
    
    -0.48
    ServletException
    -0.47
     Wikimedijinoj
    -0.47
    matchCondition
    -0.46
     reflect
    -0.44
    p
    -0.42
    POSITIVE LOGITS
     vectorielle
    0.66
    LookAnd
    0.65
     venons
    0.60
     ujednoznacz
    0.59
    دانشنامهٔ
    0.59
    ouac
    0.59
     imprimée
    0.58
    RetentionPolicy
    0.57
    htë
    0.57
    icity
    0.56
    Activations Density 24.850%

    No Known Activations