© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11203
    Prev
    Next
    INDEX
    Explanations

    code with `||`, `&&`, `[`, `==`, `getenv`, `!=`, and/or `obj`

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    TargetException
    -0.53
    下载附件
    -0.52
    thenReturn
    -0.50
     Waray
    -0.49
     UnityEditor
    -0.48
    adaptiveStyles
    -0.48
    sidemargin
    -0.45
     समीक्षाएं
    -0.44
     pulsa
    -0.44
    GIVEREF
    -0.44
    POSITIVE LOGITS
     ComVisible
    0.60
    heads
    0.54
     simplement
    0.54
    rament
    0.53
    dighet
    0.53
    sitting
    0.52
    climate
    0.51
    finish
    0.51
    DockStyle
    0.51
     necesite
    0.51
    Activations Density 0.906%

    No Known Activations