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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12484
    Prev
    Next
    INDEX
    Explanations

    a wide variety of numbers and letters, possibly related to a specific data format or coding scheme.

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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>
    -0.77
    coring
    -0.43
     tän
    -0.43
    巧
    -0.38
    iores
    -0.38
    सन्दर्भ
    -0.38
    visiting
    -0.38
    Trước
    -0.38
     ModelRenderer
    -0.38
     članak
    -0.37
    POSITIVE LOGITS
     Monfieur
    0.80
     myſelf
    0.75
     صوتيه
    0.73
     ſever
    0.72
     quæ
    0.72
     Efq
    0.72
     houſe
    0.71
     tranſ
    0.71
     Theſe
    0.71
     ſeveral
    0.70
    Activations Density 0.320%

    No Known Activations