© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7213
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Java and Javascript code

    oai_token-act-pair · gemini-2.0-flash

    removal/change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    featureID
    -0.98
    PreferredItem
    -0.79
    SpringBootTest
    -0.74
    writeFieldEnd
    -0.74
    StructEnd
    -0.73
    CppMethod
    -0.72
    tagHelperRunner
    -0.71
     GenerationType
    -0.68
    windowFixed
    -0.66
    rawDesc
    -0.66
    POSITIVE LOGITS
    ToDelete
    0.70
    Destroyed
    0.68
    ToRemove
    0.64
    ToUpdate
    0.58
    Staying
    0.57
    Voted
    0.57
    ToMove
    0.57
    Broke
    0.57
    Losing
    0.57
    Decided
    0.57
    Activations Density 7.010%

    No Known Activations