© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4675
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical parts and assembly.

    oai_token-act-pair · gemini-2.0-flash

    Openings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     opening
    -0.59
     Paglinawan
    -0.59
    )++;
    -0.57
    automne
    -0.55
     access
    -0.51
    קישורים
    -0.51
     OPENING
    -0.50
    opening
    -0.50
    Gate
    -0.50
     onData
    -0.50
    POSITIVE LOGITS
     utafitiHapana
    0.60
    
    0.56
     gynhyrchwyd
    0.54
    ValueStyle
    0.52
    moveToFirst
    0.52
    __);
    0.49
    IDENTIAL
    0.49
     AssemblyTitle
    0.47
    AsUp
    0.47
    Advisor
    0.47
    Activations Density 38.797%

    No Known Activations