© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, pronouns, and adjectives with common nouns.

    oai_token-act-pair · gemini-2.0-flash

    academic papers

    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
    Has
    -2.14
    has
    -2.06
     Has
    -2.03
     has
    -1.95
     HAS
    -1.64
    HAS
    -1.63
     hath
    -1.31
     έχει
    -1.25
     heeft
    -1.25
     имеет
    -1.22
    POSITIVE LOGITS
     disambiguazione
    0.69
    ArrowToggle
    0.66
    expandindo
    0.60
     is
    0.55
     là
    0.55
    <?
    0.53
    contentLoaded
    0.51
     cherchés
    0.49
    Попис
    0.49
    TabIndex
    0.48
    Activations Density 9.754%

    No Known Activations