© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10606
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms, particularly in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    "no"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ThroughAttribute
    -0.92
    addCriterion
    -0.91
    :✨
    -0.83
    PerformLayout
    -0.81
    TypedDataSet
    -0.75
    évaluateur
    -0.74
    ⓧ
    -0.73
    oredCriteria
    -0.72
    دانشنامهٔ
    -0.69
     ProtoMessage
    -0.68
    POSITIVE LOGITS
     se
    0.60
    <bos>
    0.55
    "}}
    0.49
     touch
    0.45
     me
    0.43
     so
    0.43
    adec
    0.43
    engertian
    0.43
     model
    0.41
     ruffled
    0.41
    Activations Density 0.304%

    No Known Activations