© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2268
    Prev
    Next
    INDEX
    Explanations

    words and phrases involving child-rearing and children's psychology

    oai_token-act-pair · gemini-2.0-flash

    family and pets

    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
     utafitiHapana
    -0.50
     المر
    -0.46
    cn
    -0.46
    cesis
    -0.46
    čios
    -0.45
     الاطلاع
    -0.44
    tholes
    -0.43
     тем
    -0.43
    Sandbox
    -0.42
    }*/
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.55
    )++;
    0.55
    ^(@)
    0.51
     Efq
    0.49
    ſelves
    0.46
    IUrlHelper
    0.45
    Демографія
    0.44
     Majefty
    0.44
     myſelf
    0.44
     himſelf
    0.43
    Activations Density 7.752%

    No Known Activations