© 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. 8236
    Prev
    Next
    INDEX
    Explanations

    non-English salutations and conversational phrases

    oai_token-act-pair · gemini-2.0-flash

    words or patterns related to programming or coding

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

    non-English text

    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
    uxxxx
    -0.78
    Cordialement
    -0.75
     Picchu
    -0.74
    دانشنامهٔ
    -0.70
     Dijo
    -0.69
     OnInit
    -0.69
    hawatir
    -0.69
     myſelf
    -0.67
     MonoBehaviour
    -0.66
     كومونز
    -0.66
    POSITIVE LOGITS
    PYX
    0.62
     Inc
    0.56
     Pre
    0.50
     S
    0.49
     Sab
    0.49
    AntiForgeryToken
    0.49
     Nos
    0.48
     No
    0.47
     pre
    0.46
     C
    0.46
    Activations Density 0.816%

    No Known Activations