© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13801
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to negative physical or mental human conditions or actions

    oai_token-act-pair · gemini-2.0-flash

    illnesses and medical research

    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
    ographed
    -0.55
    InSection
    -0.51
     Mack
    -0.48
     NSCoder
    -0.48
    rrggbb
    -0.48
     AppCompat
    -0.47
    HEET
    -0.47
    ontent
    -0.47
    󠁿
    -0.46
    ecap
    -0.45
    POSITIVE LOGITS
    migrationBuilder
    0.67
     ویکی‌پدیا
    0.65
    NameInMap
    0.63
    FieldBuilder
    0.63
     disambiguazione
    0.60
     дописавши
    0.57
    reds
    0.57
    IonicModule
    0.56
    aarrggbb
    0.56
     pulumi
    0.56
    Activations Density 8.857%

    No Known Activations