© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3422
    Prev
    Next
    INDEX
    Explanations

    words related to changing states or transformation

    oai_token-act-pair · gemini-2.0-flash

    Transformation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    脚注の使い方
    -0.55
    VersionUID
    -0.46
     सम
    -0.46
    pré
    -0.45
     chính
    -0.45
    को
    -0.44
    oo
    -0.43
     pré
    -0.42
     democrat
    -0.42
     को
    -0.41
    POSITIVE LOGITS
    InputBorder
    0.77
    webElementXpaths
    0.75
    MigrationBuilder
    0.68
    UIControlState
    0.67
    schirm
    0.64
     poffible
    0.62
    romyalgia
    0.62
     myſelf
    0.62
    TagMode
    0.61
    enumii
    0.61
    Activations Density 3.131%

    No Known Activations