© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12150
    Prev
    Next
    INDEX
    Explanations

    code snippets (possibly C++) including the underscore character and other symbols

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    but
    -0.45
     minimally
    -0.43
     but
    -0.42
     neither
    -0.42
     Neither
    -0.39
     preocupação
    -0.38
     sparingly
    -0.38
    though
    -0.38
    although
    -0.37
    但是
    -0.37
    POSITIVE LOGITS
     autorytatywna
    1.16
    rungsseite
    1.06
    Personendaten
    1.02
    دانشنامهٔ
    0.96
     NSCoder
    0.93
    StoryboardSegue
    0.92
    GraphicsUnit
    0.91
    MigrationBuilder
    0.89
     lenker
    0.86
     fieldNum
    0.85
    Activations Density 0.386%

    No Known Activations