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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1560
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that would be found in blog posts

    oai_token-act-pair · gemini-2.0-flash

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Monfieur
    -0.72
    AnimationsModule
    -0.61
    soever
    -0.60
     Jefus
    -0.58
     TextAppearance
    -0.58
     Efq
    -0.58
     تانيه
    -0.57
    MigrationBuilder
    -0.56
    MethodManager
    -0.56
     nemlig
    -0.56
    POSITIVE LOGITS
     oprot
    0.66
    ratos
    0.52
     postIndex
    0.49
    COUVER
    0.48
     Glau
    0.47
    GOTREF
    0.45
    λε
    0.43
    ipes
    0.43
    htë
    0.43
    CITATION
    0.43
    Activations Density 15.688%

    No Known Activations