© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4167
    Prev
    Next
    INDEX
    Explanations

    phrases that are used in internet forum discussions, including elements of technical/computer discussions and subjective interjections.

    oai_token-act-pair · gemini-2.0-flash

    programming help forums

    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
     vägen
    -0.80
     فريبيس
    -0.80
     سكانية
    -0.77
    UnusedPrivate
    -0.74
    دانشنامهٔ
    -0.74
    DockStyle
    -0.73
    troppo
    -0.73
     ujednoznacz
    -0.72
    IsContent
    -0.71
     beginnetje
    -0.71
    POSITIVE LOGITS
    ья
    0.56
    ts
    0.56
     os
    0.52
    EntityFramework
    0.50
    ns
    0.50
    ias
    0.50
    js
    0.49
     &
    0.49
    ons
    0.48
    on
    0.48
    Activations Density 4.543%

    No Known Activations