© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6986
    Prev
    Next
    INDEX
    Explanations

    words relevant to discussing either wind power and its impact or comparing different options in a discussion

    oai_token-act-pair · gemini-2.0-flash

    Alternate energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ibatis
    -0.52
    ptonshire
    -0.51
    Gemeinden
    -0.51
    MockBean
    -0.50
    attery
    -0.49
     vector
    -0.49
    __':
    -0.48
    enegro
    -0.48
    ]--;
    -0.46
    argout
    -0.46
    POSITIVE LOGITS
     دیکھیے
    0.55
     doInBackground
    0.55
    بوابة
    0.54
    aka
    0.54
     Rücks
    0.52
     Aç
    0.51
     متعلقه
    0.51
    באנגלית
    0.50
     căng
    0.48
    acam
    0.48
    Activations Density 0.321%

    No Known Activations