© 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. 9919
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Rep", often followed by a period

    oai_token-act-pair · gemini-2.0-flash

    references to 'Rep'

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

    Rep

    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
     الحره
    -0.68
    تقاوى
    -0.63
    zzleHttp
    -0.61
     onCreateView
    -0.59
     kasarigan
    -0.59
     Paglinawan
    -0.59
    Pyx
    -0.58
    deauna
    -0.58
     صوتيه
    -0.57
     "..\..\
    -0.54
    POSITIVE LOGITS
    CPtr
    0.65
     myſelf
    0.58
    MessageTagHelper
    0.56
     définiti
    0.52
    ніципалі
    0.49
    ◀
    0.49
    rawDesc
    0.49
    brink
    0.48
     quæ
    0.48
    mat
    0.46
    Activations Density 0.426%

    No Known Activations