© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15204
    Prev
    Next
    INDEX
    Explanations

    topics related to education, research and planning

    oai_token-act-pair · gemini-2.0-flash

    education/instruction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -1.08
    évaluateur
    -0.96
    AndEndTag
    -0.95
    setVerticalGroup
    -0.93
    RectangleBorder
    -0.87
    TagMode
    -0.85
     autorytatywna
    -0.85
     وتسجيلات
    -0.85
     HasFactory
    -0.84
    onViewCreated
    -0.83
    POSITIVE LOGITS
     hands
    0.48
     applied
    0.42
    perative
    0.41
     procedural
    0.40
     probability
    0.40
    jaro
    0.39
     statutory
    0.39
    OS
    0.39
     application
    0.38
     Koo
    0.38
    Activations Density 6.316%

    No Known Activations