© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12382
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "comp"

    oai_token-act-pair · gemini-2.0-flash

    commands or code snippets

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

    Comp

    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
    SerializedName
    -0.44
    imensional
    -0.43
    kke
    -0.42
    XtraGrid
    -0.42
    gas
    -0.42
     rangs
    -0.41
     mengak
    -0.40
    mlung
    -0.40
    compar
    -0.40
    ũ
    -0.40
    POSITIVE LOGITS
     propOrder
    0.86
    expandindo
    0.77
     فريبيس
    0.74
    )++;
    0.70
    ]--;
    0.70
    Hentet
    0.69
    preneurs
    0.68
    WebServlet
    0.67
     Ανακτήθηκε
    0.67
     doInBackground
    0.67
    Activations Density 0.561%

    No Known Activations