© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3990
    Prev
    Next
    INDEX
    Explanations

    words meaning "to lessen or sabotage something."

    oai_token-act-pair · gemini-2.0-flash

    undermining/thwarting

    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
    PreferredItem
    -0.68
    culin
    -0.61
    +#+#
    -0.60
     GenerationType
    -0.57
     synag
    -0.56
    urches
    -0.56
     MaterialApp
    -0.55
    expandindo
    -0.54
    itename
    -0.53
    OPERATOR
    -0.53
    POSITIVE LOGITS
    <bos>
    0.74
    MLLoader
    0.64
     locul
    0.59
    localctx
    0.58
    ynx
    0.56
     utafitiHapana
    0.56
     nivelul
    0.54
    seamnă
    0.52
     bronce
    0.52
    ümü
    0.52
    Activations Density 1.196%

    No Known Activations