© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    code snippets with variable declarations and get/set methods

    oai_token-act-pair · gemini-2.0-flash

    programming-related terminology or syntax

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

    }

    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
     nine
    -0.49
    9
    -0.47
     pu
    -0.46
    ver
    -0.46
     Britton
    -0.45
    丫
    -0.45
    mpa
    -0.45
     multiple
    -0.43
    ชาติ
    -0.43
    aven
    -0.42
    POSITIVE LOGITS
    expandindo
    1.03
    NameInMap
    1.03
    ագրություններ
    1.00
    AddTagHelper
    0.99
    tvguidetime
    0.90
    posedge
    0.88
     GenerationType
    0.84
     للاسماء
    0.84
    Autoritní
    0.83
     Мексичка
    0.81
    Activations Density 5.356%

    No Known Activations