© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 13321
    Prev
    Next
    INDEX
    Explanations

    the word "husband" and words of quantitative degree (deal, themselves, differ etc)

    oai_token-act-pair · gemini-2.0-flash

    husband

    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
    Negative Logits
    2
    -0.69
    .
    -0.63
    ,
    -0.59
    4
    -0.58
    1
    -0.57
    '
    -0.57
    3
    -0.56
    ;
    -0.54
    6
    -0.54
    k
    -0.53
    POSITIVE LOGITS
     AssemblyTitle
    1.12
     myſelf
    1.12
    Geplaatst
    1.07
     pleaſure
    1.07
     raiſ
    1.06
    styleType
    1.05
     doubtnut
    1.05
    ſelf
    1.05
     itſelf
    1.03
    ]));
    
    1.02
    Activations Density 0.780%

    No Known Activations