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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5978
    Prev
    Next
    INDEX
    Explanations

    technical language related to firearms

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     ModelExpression
    -0.66
    })).
    -0.65
     للاسماء
    -0.61
    Tē
    -0.61
     تكبرها
    -0.61
    BURGH
    -0.60
    }))
    
    -0.59
    Extinguishing
    -0.57
    )}_
    -0.57
     TestBed
    -0.54
    POSITIVE LOGITS
     linkovi
    0.52
     kasarigan
    0.50
    ToAction
    0.47
    etsk
    0.47
    haltens
    0.45
    addWidget
    0.45
     tokens
    0.45
    tagHelperRunner
    0.44
    Rem
    0.43
     Rem
    0.43
    Activations Density 0.472%

    No Known Activations