© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5996
    Prev
    Next
    INDEX
    Explanations

    instances of the words to, you, I, Student and the letter t in the text

    oai_token-act-pair · gemini-2.0-flash

    doing

    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
     learned
    -0.80
     development
    -0.77
     develops
    -0.74
    Development
    -0.74
     learning
    -0.73
     developing
    -0.72
    Learning
    -0.72
    DEVELOP
    -0.71
     Developing
    -0.71
     Development
    -0.70
    POSITIVE LOGITS
    gameserver
    0.65
    kloped
    0.63
    IndentedString
    0.61
     étoit
    0.55
     gynhyrchwyd
    0.53
    reactstrap
    0.51
    OGND
    0.50
    LookAnd
    0.50
    TagMode
    0.49
    pruch
    0.48
    Activations Density 4.297%

    No Known Activations