© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6355
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to algorithms and data analysis

    oai_token-act-pair · gemini-2.0-flash

    Machine learning datasets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MLLoader
    -0.64
     Bourgoin
    -0.60
    hatsu
    -0.60
    apunov
    -0.59
    rshire
    -0.58
    setAccessible
    -0.58
     vuitton
    -0.57
    SequentialGroup
    -0.56
    orteur
    -0.56
    paksa
    -0.55
    POSITIVE LOGITS
     honom
    0.50
    TestBed
    0.49
     navnet
    0.48
    ựu
    0.47
    UnknownFieldSet
    0.47
    لفة
    0.47
     Finney
    0.46
     bäst
    0.45
     religione
    0.45
     sosi
    0.45
    Activations Density 15.823%

    No Known Activations