© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4098
    Prev
    Next
    INDEX
    Explanations

    words related to judicial cases, scientific publications, and education recognition

    oai_token-act-pair · gemini-2.0-flash

    Arguments and providing evidence

    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
     couver
    -0.46
     jeweils
    -0.43
     similar
    -0.42
    and
    -0.42
    स
    -0.41
     одина
    -0.40
     bloem
    -0.40
     identically
    -0.40
     similares
    -0.40
    BUF
    -0.40
    POSITIVE LOGITS
    GraphicsUnit
    0.92
    SequentialGroup
    0.91
    RenderAtEndOf
    0.90
     متعلقه
    0.88
     <<<<<<<<<<<<<<
    0.84
    InjectAttribute
    0.83
    SharedDtor
    0.83
    cshtml
    0.83
     NSCoder
    0.82
     كومونز
    0.81
    Activations Density 17.265%

    No Known Activations