© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4555
    Prev
    Next
    INDEX
    Explanations

    the word "additional" and its variations

    oai_token-act-pair · gemini-2.0-flash

    additional

    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
     additional
    -2.34
    additional
    -2.19
     Additional
    -2.00
    Additional
    -2.00
     ADDITIONAL
    -1.86
     extra
    -1.70
     zusätzlichen
    -1.64
    ADDITIONAL
    -1.63
     zusätzliche
    -1.58
    <bos>
    -1.52
    POSITIVE LOGITS
    Bref
    0.68
    WarningLevel
    0.64
     يتيمه
    0.56
    andExpect
    0.55
     hunted
    0.52
    setVerticalGroup
    0.52
     Burrows
    0.52
    liebe
    0.51
     CreateTagHelper
    0.51
    MemoryWarning
    0.50
    Activations Density 1.042%

    No Known Activations