© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    words and symbols commonly used in computer code

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    raszamy
    -0.36
     Abonnez
    -0.35
    fromnode
    -0.34
    Constructed
    -0.34
    TestTools
    -0.33
     Avez
    -0.33
    this
    -0.32
     banget
    -0.32
    sizeCache
    -0.32
     amitié
    -0.32
    POSITIVE LOGITS
    ursor
    0.84
    CloseOperation
    0.80
    ents
    0.69
    essions
    0.69
    ension
    0.69
    orithm
    0.68
    ients
    0.68
    ressions
    0.68
    urator
    0.67
    amental
    0.67
    Activations Density 23.901%

    No Known Activations