© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5971
    Prev
    Next
    INDEX
    Explanations

    XML code, and dates

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -1.02
     beginnetje
    -1.00
     Савезне
    -0.97
    DeleteBehavior
    -0.96
     AssemblyCulture
    -0.95
     Wicidata
    -0.94
    SequentialGroup
    -0.94
     Roskov
    -0.89
    ValueStyle
    -0.87
     للمعارف
    -0.86
    POSITIVE LOGITS
    7
    1.16
    8
    1.14
    6
    1.12
    9
    1.05
    4
    1.03
    3
    1.02
    5
    1.02
    2
    0.88
     nine
    0.88
    1
    0.86
    Activations Density 13.744%

    No Known Activations