© 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. 14460
    Prev
    Next
    INDEX
    Explanations

    subjective text and reasoning within a discussion.

    oai_token-act-pair · gemini-2.0-flash

    the concept of being "still" or "not done."

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

    still

    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
    insee
    -0.52
    utilisons
    -0.52
     kaarangay
    -0.51
     ALREADY
    -0.50
    stackSize
    -0.50
     existing
    -0.50
    parsedMessage
    -0.49
     bestaande
    -0.47
    Autoritní
    -0.47
    geslacht
    -0.47
    POSITIVE LOGITS
     ainda
    1.88
     still
    1.74
    still
    1.69
     aún
    1.67
     todavía
    1.66
     noch
    1.66
     еще
    1.63
    Still
    1.59
     Still
    1.55
     jeszcze
    1.55
    Activations Density 2.898%

    No Known Activations