© 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. 5637
    Prev
    Next
    INDEX
    Explanations

    Serbian language related to sending messages

    oai_token-act-pair · gemini-2.0-flash

    actions related to sending messages

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

    sending

    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
     CreateTagHelper
    -0.57
     ddelweddau
    -0.48
     considérons
    -0.47
    RotationOrder
    -0.47
    ArrowToggle
    -0.47
    IVEREF
    -0.47
    quiel
    -0.45
    Sequence
    -0.44
    новниш
    -0.43
    gione
    -0.43
    POSITIVE LOGITS
     send
    1.05
     sending
    1.01
     sends
    0.95
     Sending
    0.91
    Sent
    0.91
     Sent
    0.90
     sent
    0.89
     Sends
    0.88
    Sending
    0.88
    send
    0.88
    Activations Density 1.187%

    No Known Activations