© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15205
    Prev
    Next
    INDEX
    Explanations

    words related to genetic diseases and mutations

    oai_token-act-pair · gemini-2.0-flash

    genetic mutations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ">//
    -0.65
    gra
    -0.50
     allmän
    -0.45
     adresa
    -0.45
    grace
    -0.44
     skär
    -0.43
     berke
    -0.41
    Grace
    -0.41
    használ
    -0.41
     адресу
    -0.41
    POSITIVE LOGITS
    AddHtmlAttribute
    0.86
     MessageBoxIcon
    0.81
    SharedCtor
    0.69
    ReusableCell
    0.67
     виправивши
    0.66
    interopRequire
    0.64
    contentLoaded
    0.63
    GraphicsUnit
    0.63
    HasIndex
    0.63
    OGND
    0.63
    Activations Density 3.818%

    No Known Activations