© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16144
    Prev
    Next
    INDEX
    Explanations

    language around medical recovery after an injury or disease, but also seems to activate for instances related to family.

    oai_token-act-pair · gemini-2.0-flash

    medical issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ISupport
    -0.83
    TagHelpers
    -0.82
     المعيارى
    -0.81
     AssemblyProduct
    -0.80
     للاسماء
    -0.76
    Espèce
    -0.75
    migrationBuilder
    -0.71
    +#+#
    -0.71
     MessageBoxIcon
    -0.70
    TProtocol
    -0.69
    POSITIVE LOGITS
     demonios
    0.43
     bő
    0.42
     vermelhas
    0.42
     szé
    0.41
     vrou
    0.41
    داشت
    0.41
     vacanza
    0.40
    열
    0.40
     drit
    0.40
    cydow
    0.40
    Activations Density 2.768%

    No Known Activations