© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1359
    Prev
    Next
    INDEX
    Explanations

    words related to medical experiments, blood and internal organs, and chemical injections and analysis

    oai_token-act-pair · gemini-2.0-flash

    blood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     blood
    -0.80
     BLOOD
    -0.77
     Blood
    -0.75
    Blood
    -0.71
     Blut
    -0.68
     sangre
    -0.66
     خون
    -0.63
    blood
    -0.60
    BLOOD
    -0.60
     bloed
    -0.59
    POSITIVE LOGITS
    nastics
    0.83
     saites
    0.75
     ivelany
    0.65
     ddelweddau
    0.60
     Efq
    0.60
     الحره
    0.59
    parametrize
    0.59
    awakeFromNib
    0.59
     kasarigan
    0.59
    WriteBarrier
    0.58
    Activations Density 5.570%

    No Known Activations