© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5343
    Prev
    Next
    INDEX
    Explanations

    closing curly braces followed by a non-zero character

    oai_token-act-pair · gemini-2.0-flash

    }

    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
    <bos>
    -2.14
    ↵
    -0.97
    '
    -0.77
    ’
    -0.77
    ↵↵
    -0.73
    ‘
    -0.56
    ,
    -0.54
    ↵↵↵
    -0.52
    (
    -0.50
      
    -0.49
    POSITIVE LOGITS
     Majefty
    0.76
    ValueStyle
    0.75
     $:$
    0.74
     Theſe
    0.71
     Diſ
    0.71
     Reſ
    0.71
     isSuccess
    0.69
     leaſt
    0.69
     purpoſe
    0.69
     Houſe
    0.68
    Activations Density 1.092%

    No Known Activations