© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10337
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to legal proceedings and future employment

    oai_token-act-pair · gemini-2.0-flash

    don/does

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Normdatei
    -0.73
    }}}
    -0.63
    </thead>
    -0.63
    สือ
    -0.58
    djangoproject
    -0.58
    Xna
    -0.56
     parlé
    -0.55
     tramonto
    -0.54
     autorytatywna
    -0.54
     goûts
    -0.53
    POSITIVE LOGITS
     don
    0.74
     dont
    0.72
    Билгалдахарш
    0.69
    Don
    0.68
    don
    0.66
    Does
    0.66
     does
    0.65
     Does
    0.64
     doesn
    0.63
     Don
    0.62
    Activations Density 3.311%

    No Known Activations