© 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. 4744
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gemini-2.0-flash

    names

    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
     himself
    -1.08
    himself
    -0.96
     Himself
    -0.88
    __':
    -0.68
     męski
    -0.66
     manhood
    -0.65
     masculinity
    -0.63
     neuter
    -0.63
     stesso
    -0.58
    くんの
    -0.58
    POSITIVE LOGITS
     herself
    0.87
     bint
    0.70
    RefreshLayout
    0.66
     she
    0.65
    حياتها
    0.65
    脚注の使い方
    0.63
    mybatisplus
    0.62
     ihren
    0.61
    PerformLayout
    0.61
    AccessorTable
    0.60
    Activations Density 9.082%

    No Known Activations