© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10702
    Prev
    Next
    INDEX
    Explanations

    language that indicates predictions or plans, especially those with "will" or "to"

    oai_token-act-pair · gemini-2.0-flash

    Entertainment news

    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
    Tikang
    -0.72
     head
    -0.68
     disambiguazione
    -0.65
    帖最后由
    -0.65
    archiviato
    -0.64
    scrapy
    -0.60
    IndentedString
    -0.60
    脚注の使い方
    -0.59
    tanleria
    -0.59
    Head
    -0.59
    POSITIVE LOGITS
    AddTagHelper
    0.54
     sign
    0.53
    promoted
    0.52
    Ārējās
    0.51
     grace
    0.49
     useCallback
    0.48
    cdt
    0.47
     Promoted
    0.46
     promoted
    0.45
     promoting
    0.45
    Activations Density 3.434%

    No Known Activations