© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    descriptions of health risk statistics

    oai_token-act-pair · gemini-2.0-flash

    deaths and casualties

    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
     death
    -1.03
    death
    -0.88
     Death
    -0.86
    Death
    -0.84
    case
    -0.68
    DEATH
    -0.68
     DEATH
    -0.63
    Case
    -0.61
     case
    -0.59
     fatality
    -0.56
    POSITIVE LOGITS
     InputDecoration
    0.66
    migrationBuilder
    0.61
     AssemblyVersion
    0.60
     فريبيس
    0.60
    ruiter
    0.59
    󠁢
    0.57
    abang
    0.56
    TAGS
    0.56
    EndProject
    0.56
    irical
    0.55
    Activations Density 12.831%

    No Known Activations