© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16194
    Prev
    Next
    INDEX
    Explanations

    mentions of evaluation and observation

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Портал
    -0.53
    見た
    -0.51
     نظر
    -0.49
     esame
    -0.47
     da
    -0.47
    èrement
    -0.46
    InputBorder
    -0.46
     common
    -0.46
    jak
    -0.46
     tarik
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.85
    bootstrapcdn
    0.71
    PerformLayout
    0.68
     distanciation
    0.68
     intptr
    0.64
    醐
    0.64
     Eſ
    0.62
     Majefty
    0.62
     ſy
    0.60
     referenties
    0.60
    Activations Density 6.208%

    No Known Activations