© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14746
    Prev
    Next
    INDEX
    Explanations

    words and phrases involving poverty and fighting against it

    oai_token-act-pair · gemini-2.0-flash

    Global issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     propOrder
    -1.20
    DockStyle
    -1.17
     Efq
    -1.05
     Houſe
    -1.04
     beginnetje
    -0.97
     ―――――
    -0.95
     Reſ
    -0.94
     Theſe
    -0.93
     itſelf
    -0.93
    WebServlet
    -0.92
    POSITIVE LOGITS
     ad
    0.46
     del
    0.45
     di
    0.45
     and
    0.43
     Ad
    0.42
     Little
    0.42
     u
    0.40
     Del
    0.39
     bes
    0.38
     у
    0.37
    Activations Density 2.322%

    No Known Activations