© 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. 9134
    Prev
    Next
    INDEX
    Explanations

    capitalized words, letters, and numbers in what looks like article citations or lists of ingredients of food

    oai_token-act-pair · gemini-2.0-flash

    say "R" words

    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
     ContentValues
    -0.51
     كومونز
    -0.49
    makeText
    -0.49
    AccessorTable
    -0.48
    ValueStyle
    -0.47
     بيها
    -0.47
     تضيفلها
    -0.46
    г
    -0.45
     OkHttpClient
    -0.43
     BitmapFactory
    -0.41
    POSITIVE LOGITS
     Row
    0.88
     Raw
    0.83
     Ro
    0.83
     Ransom
    0.81
     ROW
    0.80
     Rasa
    0.80
     Rota
    0.80
     Rat
    0.78
    Row
    0.78
     Rem
    0.77
    Activations Density 3.834%

    No Known Activations