© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11451
    Prev
    Next
    INDEX
    Explanations

    capital letters at the start of a sentence or name, and also a word that starts a sentence

    oai_token-act-pair · gemini-2.0-flash

    Pick

    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
    äsident
    -0.48
    Enllaços
    -0.47
    }>;
    -0.47
    ankind
    -0.46
    modity
    -0.46
    centralwidget
    -0.46
    UNDLE
    -0.46
    MethodManager
    -0.45
    NavController
    -0.44
    ViewInit
    -0.44
    POSITIVE LOGITS
    <bos>
    1.89
    The
    0.77
    This
    0.62
    During
    0.60
    We
    0.60
     Infórmanos
    0.60
    the
    0.60
    Zacks
    0.59
    In
    0.59
    There
    0.58
    Activations Density 1.756%

    No Known Activations