© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9291
    Prev
    Next
    INDEX
    Explanations

    code snippets with multiple programming languages represented

    oai_token-act-pair · gemini-2.0-flash

    say "an ending parenthesis"

    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
    cessite
    -0.76
     himſelf
    -0.74
    ientí
    -0.74
     Efq
    -0.73
     poffible
    -0.73
     themſelves
    -0.72
     poffe
    -0.71
    ^(@)
    -0.71
    imetsu
    -0.70
    REQUENCY
    -0.69
    POSITIVE LOGITS
     },
    
    0.85
     )}$
    0.82
     )}
    0.76
     }>
    0.74
     };
    
    0.73
     ),
    
    0.69
    >}
    0.69
    ]}>
    0.69
    ,}
    0.67
     ):
    0.67
    Activations Density 8.739%

    No Known Activations