© 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. 15037
    Prev
    Next
    INDEX
    Explanations

    words related to blood and violence

    oai_token-act-pair · gemini-2.0-flash

    blood and blood sampling

    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
     Blood
    -2.69
     blood
    -2.67
     BLOOD
    -2.53
    Blood
    -2.53
    blood
    -2.41
    BLOOD
    -2.30
    血
    -1.99
     bloed
    -1.89
     Blut
    -1.85
    的血
    -1.79
    POSITIVE LOGITS
    ftagPool
    0.53
    fromnode
    0.52
     contextLoads
    0.50
     zweck
    0.45
     DialogInterface
    0.43
     Vikipedi
    0.43
     sínt
    0.43
    Kenzie
    0.43
     tani
    0.43
     krab
    0.41
    Activations Density 2.437%

    No Known Activations