© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11568
    Prev
    Next
    INDEX
    Explanations

    code and table formatting characters

    oai_token-act-pair · gemini-2.0-flash

    symbols and formatting in code or scripts

    np_token-act-pair-logits · gpt-4o-mini

    dashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    -
    -1.57
    –
    -1.27
    -%
    -1.22
    --
    -1.17
    -,
    -1.11
    -</
    -1.07
    -(
    -1.06
    -"
    -1.05
    ----------------
    -1.02
    -',
    -1.01
    POSITIVE LOGITS
     resourceCulture
    0.98
     "..\..\
    0.75
     архивлан
    0.74
    protoimpl
    0.74
    ImageContext
    0.74
    awtextra
    0.71
     "..\..\..\
    0.71
    principalColumn
    0.71
    StoryboardSegue
    0.71
    WriteBarrier
    0.70
    Activations Density 4.660%

    No Known Activations