© 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. 14200
    Prev
    Next
    INDEX
    Explanations

    legal and scientific jargon, including acronyms, abbreviations, and specialized terms.

    oai_token-act-pair · gemini-2.0-flash

    Word prefixes and suffixes

    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
    amaño
    -0.63
    ADT
    -0.61
    magitan
    -0.61
    adeloupe
    -0.60
    OSD
    -0.59
    entibus
    -0.59
    avoit
    -0.59
    SOP
    -0.58
    ſſel
    -0.58
     resultCode
    -0.58
    POSITIVE LOGITS
    f
    0.74
    h
    0.73
    a
    0.71
    n
    0.71
    k
    0.70
    m
    0.70
    i
    0.69
    e
    0.69
    b
    0.68
    c
    0.67
    Activations Density 15.026%

    No Known Activations