© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 14318
    Prev
    Next
    INDEX
    Explanations

    phrases involving the words "this", "topic", "subject", "book" or "article".

    oai_token-act-pair · gemini-2.0-flash

    subject matter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     chng
    -0.71
     iprot
    -0.68
    Hozzáférés
    -0.64
    CodeAttribute
    -0.62
    Referències
    -0.59
    InputBorder
    -0.57
    PMailer
    -0.57
     kapag
    -0.57
    الحياه
    -0.55
     nawr
    -0.54
    POSITIVE LOGITS
     subject
    3.17
    subject
    2.66
     subjects
    2.64
     Subject
    2.63
    Subject
    2.56
     topic
    2.52
     SUBJECT
    2.34
    SUBJECT
    2.19
     Subjects
    2.17
     sujets
    2.17
    Activations Density 2.201%

    No Known Activations