© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16103
    Prev
    Next
    INDEX
    Explanations

    various kinds of technical writing, often related to math, genetics, programming, and diagrams

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
      
    -0.38
     
    -0.35
     flori
    -0.24
     F
    -0.23
     кара
    -0.22
    -
    -0.22
     عام
    -0.21
     Folsom
    -0.20
    <unused61>
    -0.20
     "
    -0.20
    POSITIVE LOGITS
    MigrationBuilder
    1.10
    脚注の使い方
    1.09
     disambiguazione
    1.06
    OGND
    1.02
     nahilalakip
    1.00
    DockStyle
    0.99
    ChildScrollView
    0.98
    StoryboardSegue
    0.98
    WriteBarrier
    0.98
     MainAxisSize
    0.96
    Activations Density 51.040%

    No Known Activations