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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11016
    Prev
    Next
    INDEX
    Explanations

    titles, locations, and short phrases

    oai_token-act-pair · 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
    Erreferentziak
    -0.60
    WebElementEntity
    -0.58
    onViewCreated
    -0.54
    ########.
    -0.53
    InitVars
    -0.52
    ifolium
    -0.52
    ыгана
    -0.51
     ModelAndView
    -0.50
    TagMode
    -0.50
     paramInt
    -0.49
    POSITIVE LOGITS
    BASELINE
    0.58
    Lähteet
    0.54
    MENAFN
    0.53
     unknow
    0.52
    copg
    0.50
     whereof
    0.50
     sleepers
    0.49
     Silurian
    0.49
    Distribuzione
    0.49
    Referències
    0.49
    Activations Density 0.387%

    No Known Activations