© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9661
    Prev
    Next
    INDEX
    Explanations

    the phrase "cut out"

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     out
    -1.09
    out
    -0.79
     Out
    -0.75
     OUT
    -0.70
    Out
    -0.65
    OUT
    -0.64
     outs
    -0.63
    アウト
    -0.56
     into
    -0.56
     fuera
    -0.54
    POSITIVE LOGITS
    ]--;
    0.88
    TagMode
    0.87
    `{.
    0.82
    styleable
    0.81
    новништво
    0.79
    AddTagHelper
    0.78
     AttributeSet
    0.77
     $_"
    0.75
    دانشنامهٔ
    0.73
     &___
    0.73
    Activations Density 0.197%

    No Known Activations