© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15501
    Prev
    Next
    INDEX
    Explanations

    words relating to bicycle repair

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to bike maintenance

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

    mechanical issues/repairs

    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
    Negative Logits
    richTextPanel
    -0.67
    Personendaten
    -0.58
    AndEndTag
    -0.56
    IntoConstraints
    -0.54
    Enllaces
    -0.52
    styleType
    -0.51
     tecnici
    -0.50
     picioare
    -0.49
    heben
    -0.49
    pone
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.59
     rust
    0.57
    ári
    0.57
    ಕ್ಕ
    0.53
    utnik
    0.53
     betweenstory
    0.52
    öch
    0.51
     failing
    0.50
     rusted
    0.50
    fjspx
    0.49
    Activations Density 0.950%

    No Known Activations