© 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. 12610
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and symbols related to technical specifications and measurements

    oai_token-act-pair · gemini-2.0-flash

    electrical components/circuits

    np_max-act-logits · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    0
    -0.42
     بيها
    -0.42
    2
    -0.39
     aastal
    -0.38
    diğinde
    -0.37
     marcha
    -0.36
    1
    -0.33
     patru
    -0.33
     ambas
    -0.33
    abilirsiniz
    -0.33
    POSITIVE LOGITS
    providedIn
    0.88
     transfieras
    0.87
    ientôt
    0.81
    >`;
    0.81
    omeness
    0.78
    новништво
    0.77
     BorderRadius
    0.75
     Majefty
    0.72
    drawal
    0.71
    intenance
    0.71
    Activations Density 6.195%

    No Known Activations