© 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. 8668
    Prev
    Next
    INDEX
    Explanations

    a collection of words with some positive and some negative sentiment, generally in the second half of the document.

    oai_token-act-pair · 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
     EconPapers
    -0.53
    PerformLayout
    -0.51
    cism
    -0.49
     insuffisamment
    -0.49
    osoba
    -0.49
     Baillargeon
    -0.46
     ब्रेकडाउन
    -0.46
     externi
    -0.46
     tématu
    -0.45
     kotlinx
    -0.45
    POSITIVE LOGITS
    awtextra
    0.60
    UserScript
    0.58
    WebVitals
    0.56
    RegisterType
    0.55
    RTSC
    0.55
    ular
    0.54
    ConstraintMaker
    0.52
    Πηγές
    0.51
     الرخصة
    0.50
     Pate
    0.50
    Activations Density 1.782%

    No Known Activations