© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12445
    Prev
    Next
    INDEX
    Explanations

    phrases meaning "full of"

    oai_token-act-pair · gemini-2.0-flash

    Filled or riddled with

    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
    RenderAtEndOf
    -1.05
    +#+#
    -0.97
     Normdatei
    -0.94
    ConstraintMaker
    -0.88
    lapsingToolbar
    -0.86
    __*/
    -0.84
     pleaſure
    -0.84
    SequentialGroup
    -0.83
     الاطلاع
    -0.82
    LEncoder
    -0.82
    POSITIVE LOGITS
    充滿
    0.55
    充满了
    0.53
    laden
    0.50
     pra
    0.48
     rich
    0.48
    populated
    0.47
    充满
    0.47
     brimming
    0.47
     A
    0.46
     suff
    0.44
    Activations Density 0.520%

    No Known Activations