© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3748
    Prev
    Next
    INDEX
    Explanations

    the "cho" trigram

    oai_token-act-pair · gemini-2.0-flash

    words or tokens starting with "cho"

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

    Cho/Chop

    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
    HIT
    -0.49
    rxjs
    -0.48
     prote
    -0.48
     Amiens
    -0.48
    anyuan
    -0.46
    (=)
    -0.46
     chế
    -0.46
     utf
    -0.44
     traffic
    -0.44
     resp
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.79
    новниш
    0.77
    хьтан
    0.72
    دانشنامهٔ
    0.69
     nahilalakip
    0.68
    RectangleBorder
    0.59
     gawas
    0.58
    исленность
    0.57
     intStringLen
    0.57
     âgées
    0.56
    Activations Density 0.378%

    No Known Activations