© 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. 9340
    Prev
    Next
    INDEX
    Explanations

    This neuron looks for mixed language text, symbols, and currency abbreviations

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or non-standard characters

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

    Location names & foreign languages

    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
     de
    -0.52
     j
    -0.51
     d
    -0.48
     f
    -0.47
     t
    -0.47
     F
    -0.47
     Far
    -0.47
     J
    -0.47
     عش
    -0.47
     dra
    -0.46
    POSITIVE LOGITS
     Majefty
    1.12
    ſelves
    1.11
    ſelf
    1.10
     itſelf
    1.06
     myſelf
    1.04
     themſelves
    1.02
     Reſ
    1.01
     ―――――
    0.98
     purpoſe
    0.96
     doubtnut
    0.94
    Activations Density 0.926%

    No Known Activations