© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13742
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessives.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    abia
    -0.49
    hores
    -0.48
    úsqueda
    -0.47
    findOneAndUpdate
    -0.47
    romat
    -0.46
    ロット
    -0.45
     yogur
    -0.45
    ARY
    -0.44
    ary
    -0.44
    тивной
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.82
    Personendaten
    0.76
     ModelExpression
    0.73
    <bos>
    0.69
    awtextra
    0.68
    AddTagHelper
    0.66
    featureID
    0.65
     незавершена
    0.65
    EndGlobalSection
    0.65
    GraphicsUnit
    0.64
    Activations Density 7.155%

    No Known Activations