© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9795
    Prev
    Next
    INDEX
    Explanations

    various separator characters and markup used in web content

    oai_token-act-pair · gemini-2.0-flash

    |

    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
    Välislingid
    -0.66
    :✨
    -0.65
    تقاوى
    -0.64
     يتيمه
    -0.62
    principalTable
    -0.60
    ValueStyle
    -0.58
     jScrollPane
    -0.56
    хьтан
    -0.56
     gainera
    -0.56
     esternos
    -0.55
    POSITIVE LOGITS
     IBOutlet
    0.54
    ksikon
    0.51
     }}"></
    0.48
     uſed
    0.48
     reft
    0.47
     Elector
    0.47
    ituary
    0.47
    }],
    0.47
    ArgsConstructor
    0.46
    omys
    0.46
    Activations Density 1.169%

    No Known Activations