© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9626
    Prev
    Next
    INDEX
    Explanations

    HTML code related to hyperlinks and buttons

    oai_token-act-pair · gemini-2.0-flash

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    はじめに
    -0.55
     Limited
    -0.51
    hafen
    -0.50
     propOrder
    -0.48
    RenderAtEndOf
    -0.47
     hạn
    -0.46
    捷
    -0.44
    Limited
    -0.43
    prepareStatement
    -0.42
     No
    -0.42
    POSITIVE LOGITS
    +#+#
    0.85
    AndEndTag
    0.76
    principalTable
    0.71
     chofe
    0.70
    évaluateur
    0.70
    SequentialGroup
    0.69
    存于互联网档案馆
    0.69
    GEBURTSDATUM
    0.68
     esternos
    0.66
     ſeveral
    0.65
    Activations Density 1.107%

    No Known Activations