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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 14352
    Prev
    Next
    INDEX
    Explanations

    somewhat technical, scientific, and legal words and phrases

    oai_token-act-pair · gemini-2.0-flash

    HTML fragments

    np_max-act · gemini-2.0-flash

    code snippets

    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
     Majefty
    -1.19
     purpoſe
    -1.13
     pleaſure
    -1.10
     raiſ
    -1.08
     ſtate
    -1.05
     Reſ
    -1.05
     whoſe
    -1.02
     Anſ
    -1.00
     faſt
    -0.99
     leaſt
    -0.98
    POSITIVE LOGITS
    LookAnd
    0.82
    RTLD
    0.82
     CreateTagHelper
    0.82
    ---*/
    0.77
    ]';
    0.76
     ]];
    0.75
    ']):
    0.75
    '])
    
    0.72
    ']);
    
    0.71
    '}}>
    0.71
    Activations Density 21.962%

    No Known Activations