© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11206
    Prev
    Next
    INDEX
    Explanations

    numbers of varying lengths, often in parentheses or associated with symbols like '$', '%', or '*'.

    oai_token-act-pair · gemini-2.0-flash

    Numerical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCulture
    -0.47
    ITICAL
    -0.46
    pherals
    -0.44
     sampai
    -0.44
    ratic
    -0.44
     Lott
    -0.42
    GMENT
    -0.42
    부터
    -0.41
     kind
    -0.41
    CloseOperation
    -0.41
    POSITIVE LOGITS
    ########.
    0.65
     nahilalakip
    0.64
     ]
    0.64
     contextLoads
    0.62
     transfieras
    0.61
     Houſe
    0.60
    expandindo
    0.59
    UnitTesting
    0.58
     Reſ
    0.58
    findpost
    0.57
    Activations Density 40.628%

    No Known Activations