© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7664
    Prev
    Next
    INDEX
    Explanations

    mentions of laboratory procedures, particularly statistical or genetic analysis

    oai_token-act-pair · gemini-2.0-flash

    performed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     liitty
    -0.63
     vastaan
    -0.59
     kysy
    -0.57
     számára
    -0.52
    ::-
    -0.50
     dochter
    -0.50
     érde
    -0.49
     coscienza
    -0.48
     kanya
    -0.48
     récompenses
    -0.47
    POSITIVE LOGITS
     BoxFit
    0.81
     betweenstory
    0.79
     AttributeSet
    0.75
    évaluateur
    0.75
     ModelExpression
    0.73
    <bos>
    0.71
    AccessorTable
    0.68
    )");
    0.66
    ibatis
    0.66
    ViewFeatures
    0.65
    Activations Density 2.761%

    No Known Activations