© 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. 7397
    Prev
    Next
    INDEX
    Explanations

    dates and historical context, often including terms like "since," "history," "period," and specific centuries.

    oai_token-act-pair · gemini-2.0-flash

    history and time periods

    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
    EARLY
    -0.78
     صوتيه
    -0.68
     early
    -0.67
    early
    -0.64
     EARLY
    -0.64
    Early
    -0.60
    ELTS
    -0.59
     Early
    -0.58
    ancient
    -0.58
    locaust
    -0.57
    POSITIVE LOGITS
     resourceCulture
    0.69
    帖最后由
    0.60
    клопе
    0.55
    ftagPool
    0.51
    Inf
    0.49
    webElementXpaths
    0.48
    omar
    0.47
    Източници
    0.47
    ➟
    0.46
    bootstrapcdn
    0.46
    Activations Density 9.287%

    No Known Activations