© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    fragmented text about business news and medical symptoms

    oai_token-act-pair · gemini-2.0-flash

    factual/scientific writing

    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
     confusion
    -0.67
     inaccurate
    -0.66
     erroneous
    -0.64
     erratic
    -0.60
     confounding
    -0.59
     embarrassing
    -0.58
     misguided
    -0.58
     misleading
    -0.57
     misunder
    -0.57
     interruption
    -0.57
    POSITIVE LOGITS
    PhysRevD
    0.69
     الحره
    0.63
     autorytatywna
    0.63
    Ծանոթ
    0.60
    twimg
    0.60
    رشف
    0.57
     AssemblyCulture
    0.56
     artikkelen
    0.56
    __":
    0.56
     vectorielles
    0.55
    Activations Density 3.998%

    No Known Activations