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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7279
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gemini-2.0-flash

    Cuth

    np_max-act · gemini-2.0-flash
    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
    '
    -1.17
    2
    -0.98
    3
    -0.97
    6
    -0.96
    7
    -0.94
    ’
    -0.90
    5
    -0.90
    4
    -0.90
     concor
    -0.89
    0
    -0.89
    POSITIVE LOGITS
    ⓧ
    1.83
     propOrder
    1.76
     betweenstory
    1.73
    )");
    
    1.69
    ")));
    
    1.67
     дописавши
    1.66
    ]")]
    1.66
    "]);
    
    1.63
     '\\;'
    1.63
    })*/
    1.59
    Activations Density 21.996%

    No Known Activations