© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9672
    Prev
    Next
    INDEX
    Explanations

    words pertaining to scientific research and study findings, or words about needing/requiring something

    oai_token-act-pair · gemini-2.0-flash

    required

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     needed
    -1.70
     required
    -1.45
    needed
    -1.44
     Needed
    -1.41
    Needed
    -1.28
    required
    -1.24
     desired
    -1.18
     NEEDED
    -1.16
    Required
    -1.10
     Required
    -1.09
    POSITIVE LOGITS
    MigrationBuilder
    1.05
    ConstraintMaker
    0.81
     дописавши
    0.75
    mybatisplus
    0.75
    featureID
    0.75
    ftagPool
    0.74
    
    0.73
     AssemblyCulture
    0.73
    BagConstraints
    0.73
     ExecuteAsync
    0.71
    Activations Density 11.516%

    No Known Activations