© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13201
    Prev
    Next
    INDEX
    Explanations

    LaTeX math code

    oai_token-act-pair · gemini-2.0-flash

    ampersand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Houſe
    -0.59
     doubtnut
    -0.57
     houſe
    -0.56
     Theſe
    -0.52
     Всё
    -0.51
     Diſ
    -0.50
    mişti
    -0.49
    ^(@)
    -0.49
     themſelves
    -0.48
     Majefty
    -0.48
    POSITIVE LOGITS
    <bos>
    0.59
    CppCodeGen
    0.58
    GraphicsUnit
    0.53
    Xna
    0.50
    Географиясе
    0.49
    DeleteBehavior
    0.47
     LUMP
    0.47
    CPtr
    0.46
    ніципалі
    0.45
    sidemargin
    0.45
    Activations Density 4.507%

    No Known Activations