© 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. 7305
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation and location names

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     Efq
    -1.06
     ―――――
    -0.97
     Monfieur
    -0.95
     Theſe
    -0.93
     myſelf
    -0.89
    ſelf
    -0.86
     ――――――――
    -0.85
     Eſ
    -0.85
     Anſ
    -0.83
     itſelf
    -0.83
    POSITIVE LOGITS
    ↵↵
    0.28
    Pro
    0.27
    In
    0.26
    At
    0.26
     apropi
    0.26
    T
    0.25
    As
    0.25
    G
    0.25
    Hungry
    0.25
    App
    0.25
    Activations Density 4.256%

    No Known Activations