© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11346
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and positive feedback.

    oai_token-act-pair · gemini-2.0-flash

    appreciation words or phrases

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

    appreciation

    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
     dann
    -0.49
     ?",
    -0.46
     empfehlen
    -0.46
    はじめに
    -0.45
    seg
    -0.45
    ],
    -0.44
     maka
    -0.43
    "}")
    -0.43
    Then
    -0.43
     then
    -0.43
    POSITIVE LOGITS
     appreciate
    0.78
     Appreciate
    0.75
    ItemBackground
    0.71
     appreciated
    0.69
     contextLoads
    0.68
     appreciates
    0.68
    MigrationBuilder
    0.66
     apprécier
    0.66
     quæ
    0.65
    appreciated
    0.65
    Activations Density 2.398%

    No Known Activations