© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15228
    Prev
    Next
    INDEX
    Explanations

    words ending in "izing", occasionally picking up on words related to surveillance and words related to culture.

    oai_token-act-pair · gemini-2.0-flash

    -ifying or -izing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tifying
    -1.41
     betweenstory
    -1.32
    ppling
    -1.30
    orsing
    -1.27
    cribing
    -1.26
    tening
    -1.25
    tling
    -1.22
    angering
    -1.19
     дописавши
    -1.18
    roring
    -1.17
    POSITIVE LOGITS
     going
    0.85
     using
    0.85
    e
    0.81
     saying
    0.78
    ly
    0.77
    a
    0.77
     taking
    0.76
     working
    0.75
     looking
    0.71
     running
    0.69
    Activations Density 2.864%

    No Known Activations