© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10945
    Prev
    Next
    INDEX
    Explanations

    words and phrases which would appear in technical documentation or tutorials, possibly for software.

    oai_token-act-pair · gemini-2.0-flash

    activation/enabling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    дото
    -0.57
    リカ
    -0.48
     qu
    -0.47
     F
    -0.45
     She
    -0.44
    忱
    -0.44
    ierno
    -0.44
    +:+
    -0.43
    ò
    -0.43
     micro
    -0.43
    POSITIVE LOGITS
     Monfieur
    0.80
     Theſe
    0.77
     Efq
    0.74
     myſelf
    0.73
    脚注の使い方
    0.71
     Majefty
    0.71
     Eſ
    0.69
     whoſe
    0.67
     ſeveral
    0.67
    Autoritní
    0.66
    Activations Density 2.247%

    No Known Activations