© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8714
    Prev
    Next
    INDEX
    Explanations

    sentence or fragment endings (usually periods) followed or preceded by other determiners such as conjunctions, pronouns, or articles.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     rapides
    -0.49
    rija
    -0.46
     orina
    -0.43
     progreso
    -0.43
    gridx
    -0.42
     holde
    -0.42
     eius
    -0.41
    poir
    -0.41
     vuoto
    -0.41
     anglick
    -0.41
    POSITIVE LOGITS
     unknownFields
    0.78
    Попис
    0.71
    новниш
    0.68
     Numerade
    0.63
    PyExc
    0.63
    ,:),
    0.62
    GEBURTS
    0.61
    ConstraintMaker
    0.60
    SequentialGroup
    0.60
     AssemblyTitle
    0.60
    Activations Density 0.733%

    No Known Activations