© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    short utility words such as prepositions, conjunctions, articles, and some common verbs, often acting as glue between content words

    oai_token-act-pair · gemini-2.0-flash

    sharing of ideas

    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
    ChildScrollView
    -0.58
    PositiveButton
    -0.47
     gob
    -0.46
     broaden
    -0.46
    InputBorder
    -0.45
    siasme
    -0.44
     Ditto
    -0.44
     Superhosts
    -0.44
     Darlene
    -0.43
    Hz
    -0.43
    POSITIVE LOGITS
    TagMode
    0.66
    __()
    0.58
    Identyfik
    0.56
     تضيفلها
    0.54
     cuivre
    0.54
     ModelExpression
    0.53
    afficheront
    0.52
    formik
    0.51
    ربای
    0.50
     macrop
    0.50
    Activations Density 24.185%

    No Known Activations