© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4880
    Prev
    Next
    INDEX
    Explanations

    words used in legal or formal settings to present or evaluate an argument with consideration.

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating togetherness or conjunction

    np_token-act-pair-logits · gpt-4o-mini

    Together

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    зулта
    -0.48
     BoxFit
    -0.40
    rungsseite
    -0.40
    kování
    -0.39
    ild
    -0.38
    ushin
    -0.38
    contentLoaded
    -0.37
    пке
    -0.37
    HttpConnection
    -0.37
     Park
    -0.36
    POSITIVE LOGITS
     along
    2.70
    along
    2.58
     Along
    2.45
     ALONG
    2.45
     together
    2.41
     junto
    2.39
    Along
    2.38
     alongside
    2.23
    together
    2.20
     juntamente
    2.20
    Activations Density 3.265%

    No Known Activations