© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9647
    Prev
    Next
    INDEX
    Explanations

    words relating to both "primitive" conditions and to the "modern" slave trade

    oai_token-act-pair · gemini-2.0-flash

    descriptive writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     d
    -0.43
     dre
    -0.42
     but
    -0.42
     in
    -0.42
     that
    -0.41
    工
    -0.41
    ,
    -0.40
    end
    -0.40
    PRET
    -0.39
    ModelAndView
    -0.39
    POSITIVE LOGITS
     varandra
    0.86
    tvguidetime
    0.83
    fjspx
    0.80
     myſelf
    0.79
    ſelf
    0.78
     Theſe
    0.78
     bäst
    0.78
     CURIAM
    0.77
     autorytatywna
    0.76
     purpoſe
    0.76
    Activations Density 3.613%

    No Known Activations