© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6552
    Prev
    Next
    INDEX
    Explanations

    mentions of limits or improvements on ceilings and other limits

    oai_token-act-pair · gemini-2.0-flash

    ceiling

    np_max-act · gemini-2.0-flash

    ceiling

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    <bos>
    -1.17
    '],
    
    -0.95
    "],
    
    -0.93
    ]:
    
    -0.84
     Мексичка
    -0.82
    "])
    
    -0.82
    `,
    
    -0.79
    ]")]
    -0.78
     الرياضيه
    -0.77
    ']],
    -0.77
    POSITIVE LOGITS
     sauvages
    1.10
     médicaux
    1.06
     dieux
    0.99
     juridiques
    0.98
     ordinaires
    0.98
     nationaux
    0.96
     banques
    0.93
     normaux
    0.93
     enfans
    0.91
     investissements
    0.89
    Activations Density 2.969%

    No Known Activations