© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7394
    Prev
    Next
    INDEX
    Explanations

    the word "cut" and related phrases

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "cut"

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

    cut

    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
    IntoConstraints
    -0.90
    AndEndTag
    -0.88
    awtextra
    -0.79
    RenderAtEndOf
    -0.71
     AssemblyProduct
    -0.68
    IonicModule
    -0.68
     Efq
    -0.67
    WebVitals
    -0.67
     MotionEvent
    -0.67
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
     off
    0.45
    Koordin
    0.44
     through
    0.42
    back
    0.38
    !*\
    0.37
    lesi
    0.36
     back
    0.34
    M
    0.33
     crown
    0.33
     مناس
    0.33
    Activations Density 1.288%

    No Known Activations