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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9520
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    numerusform
    -0.57
    neurial
    -0.55
     suivante
    -0.52
     ſhould
    -0.50
    från
    -0.49
     connues
    -0.49
     whoſe
    -0.49
    GAG
    -0.48
     connus
    -0.47
    OfWork
    -0.47
    POSITIVE LOGITS
    )):
    
    0.71
    }]
    
    0.69
    __':
    
    0.68
    '):
    
    0.66
    })();
    
    0.64
    }],
    
    0.62
    ValueStyle
    0.61
    "):
    
    0.60
    adaptiveStyles
    0.60
    ]}"
    0.58
    Activations Density 12.272%

    No Known Activations