© 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. 7526
    Prev
    Next
    INDEX
    Explanations

    words related to space and, to a lesser extent, India

    oai_token-act-pair · gemini-2.0-flash

    technical terms and phrases

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

    non-English fragments

    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
     الرياضيه
    -0.58
     Tana
    -0.54
     billets
    -0.52
     Paglinawan
    -0.52
    illets
    -0.51
     bise
    -0.51
     TQ
    -0.51
     SECRET
    -0.51
     FY
    -0.51
    Viki
    -0.51
    POSITIVE LOGITS
     SwitchCompat
    0.56
    Abp
    0.52
    ---*/
    0.51
    <?
    0.48
    glises
    0.48
     transfieras
    0.48
    kuuta
    0.45
    重的
    0.45
    béco
    0.44
    Vidite
    0.44
    Activations Density 0.614%

    No Known Activations