© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4040
    Prev
    Next
    INDEX
    Explanations

    verbs related to communication or movement with a negative connotation

    oai_token-act-pair · gemini-2.0-flash

    around

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DoubleQuotes
    -0.64
    ⓧ
    -0.63
     Watched
    -0.57
    ReusableCell
    -0.57
    TagMode
    -0.57
    RepeatedField
    -0.56
    Geplaatst
    -0.55
     Majefty
    -0.54
    URIComponent
    -0.54
     sī
    -0.54
    POSITIVE LOGITS
     everywhere
    0.68
     partout
    0.67
     streets
    0.58
     newBuilder
    0.52
     around
    0.52
    Everywhere
    0.52
    各个
    0.52
     Everywhere
    0.52
    everywhere
    0.51
    مصادر
    0.50
    Activations Density 1.235%

    No Known Activations