© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13518
    Prev
    Next
    INDEX
    Explanations

    multiline comments in code

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.48
    pu
    -0.43
    ovac
    -0.43
    vor
    -0.40
    blo
    -0.39
     tu
    -0.39
    крови
    -0.39
    ρω
    -0.38
    Configurer
    -0.38
    ='"+
    -0.38
    POSITIVE LOGITS
     Efq
    0.84
     Jefus
    0.72
     myſelf
    0.69
     Theſe
    0.68
     Majefty
    0.68
     Monfieur
    0.68
     ſeveral
    0.64
     pleaſure
    0.62
     themſelves
    0.60
     itſelf
    0.59
    Activations Density 0.091%

    No Known Activations