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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10280
    Prev
    Next
    INDEX
    Explanations

    laboratory descriptions involving chemical compounds and processes

    oai_token-act-pair · gemini-2.0-flash

    clear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    سكرية
    -0.64
     Roskov
    -0.61
    MigrationBuilder
    -0.61
    gameserver
    -0.61
     stammen
    -0.60
    oa̍t
    -0.60
     Alca
    -0.59
    awtextra
    -0.59
     Kenobi
    -0.57
     SqlCommand
    -0.57
    POSITIVE LOGITS
     clear
    0.55
    clear
    0.47
    例文帳に追加
    0.46
     Clear
    0.45
     vô
    0.45
     clearer
    0.45
    請繼續往下閱讀
    0.44
    undi
    0.44
    Clear
    0.44
    比
    0.43
    Activations Density 2.192%

    No Known Activations