© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10615
    Prev
    Next
    INDEX
    Explanations

    words starting with "nar," "lar," "dar," or "amar" and sometimes words ending in "sim."

    oai_token-act-pair · gemini-2.0-flash

    names with "nar" and "dar"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kasarigan
    -1.00
    astify
    -0.85
    esez
    -0.83
     Paglinawan
    -0.80
    ChildScrollView
    -0.79
    HomeAsUpEnabled
    -0.78
    IContainer
    -0.76
    principalTable
    -0.74
    Tikang
    -0.74
    SourceChecksum
    -0.73
    POSITIVE LOGITS
    史
    0.38
    sp
    0.37
    untura
    0.36
    代
    0.35
    enden
    0.35
    ge
    0.35
    gen
    0.34
     humain
    0.34
    umpf
    0.34
    ID
    0.34
    Activations Density 0.768%

    No Known Activations