© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10357
    Prev
    Next
    INDEX
    Explanations

    the word "correlation" and its related forms like covariance.

    oai_token-act-pair · gemini-2.0-flash

    correlation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -1.61
    #
    -0.44
     raiſ
    -0.43
     plads
    -0.40
    Im
    -0.39
     vengo
    -0.39
    First
    -0.39
    ñores
    -0.38
     Tiefe
    -0.38
     ſtate
    -0.37
    POSITIVE LOGITS
    enumi
    0.80
    sidemargin
    0.76
    complexContent
    0.75
     HasFactory
    0.75
    fromnode
    0.74
    حياته
    0.71
     مشين
    0.69
    CBSE
    0.69
    UIControlState
    0.69
    )’
    0.68
    Activations Density 3.434%

    No Known Activations