© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10308
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal narrative and problem-solving in technical contexts.

    oai_token-act-pair · gemini-2.0-flash

    words indicating time references

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

    "today" and related

    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
    っそ
    -0.47
     üzere
    -0.46
    ვი
    -0.44
    matchCondition
    -0.44
    jährigen
    -0.44
    Referenties
    -0.43
     gangen
    -0.42
    ènements
    -0.42
    mota
    -0.41
     preciso
    -0.41
    POSITIVE LOGITS
     today
    3.27
     Today
    2.78
    today
    2.77
    Today
    2.67
     yesterday
    2.38
     TODAY
    2.36
     tonight
    2.36
     heute
    2.27
     todays
    2.23
     hoje
    2.20
    Activations Density 4.452%

    No Known Activations