© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6627
    Prev
    Next
    INDEX
    Explanations

    words of possibility, permission, or advisability

    oai_token-act-pair · gemini-2.0-flash

    may might

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     photolibrary
    -0.80
     Efq
    -0.74
     كومونز
    -0.73
    AccessorTable
    -0.72
     numberWith
    -0.72
    ✨:
    -0.71
    might
    -0.70
     igång
    -0.69
    Географија
    -0.68
     Paglinawan
    -0.68
    POSITIVE LOGITS
     very
    0.71
     or
    0.66
     well
    0.63
     pick
    0.61
     as
    0.60
    well
    0.57
     not
    0.54
     catch
    0.54
    care
    0.52
     Very
    0.52
    Activations Density 2.947%

    No Known Activations