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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2296
    Prev
    Next
    INDEX
    Explanations

    software code contexts, particularly related to web requests and configuration

    oai_token-act-pair · gemini-2.0-flash

    Code and API calls

    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
    anskje
    -0.81
     true
    -0.69
     hayvan
    -0.66
     faſt
    -0.64
     poffible
    -0.64
     bailarina
    -0.63
    cnia
    -0.63
     devenus
    -0.62
    true
    -0.61
     gethan
    -0.61
    POSITIVE LOGITS
     ]
    
    0.66
    +'</
    0.64
    ]:
    
    0.62
     }</
    0.59
    providedIn
    0.59
    ]='\
    0.55
    WireFormatLite
    0.54
     is
    0.53
    }")
    
    0.50
     resourceCulture
    0.49
    Activations Density 14.539%

    No Known Activations