© 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. 4256
    Prev
    Next
    INDEX
    Explanations

    legal language, particularly related to crimes and penalties

    oai_token-act-pair · gemini-2.0-flash

    legal terminology relating to crimes

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

    jargon

    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
    GenerationType
    -0.57
     Queens
    -0.50
    ✨:
    -0.47
     mdi
    -0.46
    Ẩ
    -0.46
    Master
    -0.46
    ajah
    -0.46
     진
    -0.45
     gainera
    -0.45
    XtraGrid
    -0.45
    POSITIVE LOGITS
    Datuak
    0.58
    glBind
    0.53
    InputTagHelper
    0.52
     calendriers
    0.51
    AFX
    0.51
    itoneal
    0.50
    vinas
    0.50
    AndView
    0.49
    Blink
    0.49
     cavallo
    0.48
    Activations Density 0.263%

    No Known Activations