© 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. 14662
    Prev
    Next
    INDEX
    Explanations

    passages related to health and medical advice

    oai_token-act-pair · gemini-2.0-flash

    health

    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
     worth
    -0.62
    исленность
    -0.52
    ühungen
    -0.51
    rollable
    -0.48
    Worth
    -0.47
    Below
    -0.47
     Worth
    -0.47
    </caption>
    -0.46
    )});
    -0.46
    umblebee
    -0.46
    POSITIVE LOGITS
     venons
    0.57
     onResponse
    0.57
    IActionResult
    0.56
     household
    0.56
    CodedInputStream
    0.56
     Picchu
    0.55
    SequentialGroup
    0.54
    PreferredItem
    0.54
    XmlIgnore
    0.54
    ContextCompat
    0.53
    Activations Density 2.114%

    No Known Activations