© 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. 139
    Prev
    Next
    INDEX
    Explanations

    descriptions of people being injured or killed

    oai_token-act-pair · gemini-2.0-flash

    death and violence

    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
     iprot
    -0.53
    esu
    -0.48
    euse
    -0.47
    dits
    -0.45
    égard
    -0.45
    ExtendWith
    -0.44
    iseerd
    -0.44
    webdriver
    -0.44
    こち
    -0.44
    نز
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.71
    تقاوى
    0.61
     Drapeau
    0.59
    GeoNames
    0.58
    HomeAsUpEnabled
    0.57
     armado
    0.56
    Aiheesta
    0.56
     Óscar
    0.54
    PhysRevLett
    0.54
    enterOuterAlt
    0.54
    Activations Density 7.304%

    No Known Activations