© 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
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13797
    Prev
    Next
    INDEX
    Explanations

    references to publications and legal materials.

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ↵↵↵↵
    -0.52
    andoah
    -0.49
     "
    -0.46
    ।
    -0.46
    :@"
    -0.46
     verdi
    -0.46
    )];
    -0.45
    }\
    -0.45
    }:
    -0.45
     ret
    -0.45
    POSITIVE LOGITS
     Efq
    0.84
     purpoſe
    0.83
     nakalista
    0.81
     ExecuteAsync
    0.79
     виправивши
    0.77
     pleaſure
    0.77
     utafitiHapana
    0.76
     Monfieur
    0.75
    capace
    0.72
     fubject
    0.72
    Activations Density 3.554%

    No Known Activations