© 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. 5885
    Prev
    Next
    INDEX
    Explanations

    the prefix "en" (especially in the word "en banc") and French sentence beginnings

    oai_token-act-pair · gemini-2.0-flash

    Multiple languages

    np_max-act-logits · gemini-2.0-flash

    ▁en

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     suivantes
    -0.84
    osoba
    -0.81
     pourtant
    -0.74
     bonnes
    -0.73
     noires
    -0.73
     vrais
    -0.73
     tidigare
    -0.72
     tartalomajánló
    -0.72
     članak
    -0.72
     naturelles
    -0.72
    POSITIVE LOGITS
     Monfieur
    0.29
     ſeveral
    0.28
     特写
    0.26
     Shakspeare
    0.25
    ButterKnife
    0.25
     pathfinder
    0.24
     图解
    0.24
     fhew
    0.23
     ſmall
    0.23
     Italij
    0.23
    Activations Density 0.501%

    No Known Activations