© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15059
    Prev
    Next
    INDEX
    Explanations

    fragments of sentences including punctuation or discourse markers, sometimes within dialog.

    oai_token-act-pair · gemini-2.0-flash

    specific formatting or symbols

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    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
     it
    -0.85
    它
    -0.69
     оно
    -0.60
    它是
    -0.59
    It
    -0.57
     nó
    -0.54
    VolleyError
    -0.53
    it
    -0.52
     ней
    -0.51
    nó
    -0.50
    POSITIVE LOGITS
     MenuView
    0.68
    saraba
    0.65
    '>{
    0.65
    entiel
    0.63
    bibinfo
    0.63
    在他
    0.61
    BibitemShut
    0.60
     himſelf
    0.60
    transQ
    0.59
    łby
    0.59
    Activations Density 1.440%

    No Known Activations