Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6926
    Prev
    Next
    INDEX
    Explanations

    medical case reports, specifically noting patient characteristics and symptoms.

    oai_token-act-pair · gemini-2.0-flash

    suffering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AndEndTag
    -0.85
     محفوظة
    -0.65
    tvguidetime
    -0.63
     IBOutlet
    -0.62
     wireType
    -0.59
     engraçadas
    -0.58
    AccessFile
    -0.57
    ReusableCell
    -0.57
    AddTagHelper
    -0.56
     onPostExecute
    -0.56
    POSITIVE LOGITS
     suffer
    0.63
     suffering
    0.61
     experiencing
    0.55
     received
    0.54
     suffers
    0.52
     receiving
    0.51
     suffered
    0.50
     having
    0.47
    omials
    0.47
     undergoing
    0.44
    Activations Density 2.674%

    No Known Activations