© 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. 7770
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Con."

    oai_token-act-pair · gemini-2.0-flash

    Con

    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
    +#+#
    -1.16
    interopRequire
    -0.89
     Réponses
    -0.88
    xase
    -0.88
     فريبيس
    -0.88
    OrWhiteSpace
    -0.86
     digress
    -0.86
    writeField
    -0.86
    ]),
    
    -0.85
    --]
    -0.85
    POSITIVE LOGITS
     of
    0.62
     in
    0.60
     with
    0.58
     on
    0.53
     africain
    0.52
     at
    0.49
     to
    0.49
     prieten
    0.49
     ordinaire
    0.49
     left
    0.48
    Activations Density 0.915%

    No Known Activations