© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3238
    Prev
    Next
    INDEX
    Explanations

    code snippets, symbols and variables from various programming languages as well as fragments of online forum posts

    oai_token-act-pair · gemini-2.0-flash

    d

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.68
     doubtnut
    -1.48
     Theſe
    -1.46
     Efq
    -1.41
     Houſe
    -1.37
     Majefty
    -1.36
     myſelf
    -1.33
     itſelf
    -1.30
     Anſ
    -1.26
    <bos>
    -1.25
    POSITIVE LOGITS
     M
    1.39
     G
    1.34
     C
    1.31
     F
    1.30
     R
    1.30
     E
    1.27
     B
    1.27
     P
    1.26
     D
    1.24
     L
    1.20
    Activations Density 3.402%

    No Known Activations