© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8826
    Prev
    Next
    INDEX
    Explanations

    language used in requests

    oai_token-act-pair · gemini-2.0-flash

    gratitude and happiness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     américains
    -0.73
     speranza
    -0.68
     république
    -0.68
     varandra
    -0.68
    InSection
    -0.68
     felicità
    -0.68
     termica
    -0.67
     precisione
    -0.65
     caduta
    -0.63
     statunitense
    -0.63
    POSITIVE LOGITS
     more
    0.48
     real
    0.48
    最快更新
    0.47
    mockito
    0.46
    More
    0.46
    KURZBESCHREIBUNG
    0.45
    有多
    0.44
    exports
    0.44
    <!
    0.44
    zdo
    0.43
    Activations Density 3.783%

    No Known Activations