© 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. 9160
    Prev
    Next
    INDEX
    Explanations

    technical or scientific language, including references, symbols, and numbers

    oai_token-act-pair · gemini-2.0-flash

    Business administration

    np_max-act-logits · gemini-2.0-flash

    organizational nouns

    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
    ifying
    -0.53
    entially
    -0.52
    tifies
    -0.52
    rily
    -0.49
    it
    -0.49
    soever
    -0.49
    AnchorStyles
    -0.48
    izing
    -0.47
    ulously
    -0.47
    kheim
    -0.47
    POSITIVE LOGITS
    programme
    0.96
    committee
    0.90
    company
    0.85
    departments
    0.83
    publication
    0.81
    contribution
    0.81
    application
    0.81
    economy
    0.79
    agenda
    0.79
    guidelines
    0.79
    Activations Density 39.308%

    No Known Activations