© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5381
    Prev
    Next
    INDEX
    Explanations

    numbers indicating an amount of memory or disk space

    oai_token-act-pair · gemini-2.0-flash

    Computer memory sizes

    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
    Tembelea
    -0.91
     المعيارى
    -0.72
    istoitu
    -0.70
     صوتيه
    -0.68
    aarrggbb
    -0.65
     tarif
    -0.61
    ChildScrollView
    -0.60
     cáp
    -0.59
    ollection
    -0.57
    bolista
    -0.56
    POSITIVE LOGITS
    TypedDataSet
    0.60
    mb
    0.58
    MB
    0.58
    M
    0.51
    sist
    0.51
     MB
    0.49
    aspectj
    0.46
    edb
    0.45
    G
    0.45
    ai
    0.44
    Activations Density 1.532%

    No Known Activations