© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12274
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to the ancient world and prehistoric times

    oai_token-act-pair · gemini-2.0-flash

    ancient times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    腾
    -0.56
    ISupport
    -0.46
    <bos>
    -0.44
     Sen
    -0.43
     vừa
    -0.40
    rylic
    -0.40
    erts
    -0.40
    覧
    -0.39
    DebuggerNonUser
    -0.39
    léans
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.78
     ExecuteAsync
    0.75
     FetchType
    0.66
     Spisak
    0.65
    سطس
    0.63
     snippetHide
    0.63
    tagext
    0.63
     InputDecoration
    0.63
    ريكية
    0.62
    +#+#
    0.61
    Activations Density 0.468%

    No Known Activations