© 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. 4109
    Prev
    Next
    INDEX
    Explanations

    SQL code

    oai_token-act-pair · gemini-2.0-flash

    SQL queries

    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
     Audiodateien
    -0.59
     spooky
    -0.57
     BoxDecoration
    -0.55
     giggles
    -0.54
     chameleon
    -0.54
     growl
    -0.54
     vampires
    -0.53
     Rambo
    -0.53
    interopRequire
    -0.53
     creepy
    -0.51
    POSITIVE LOGITS
     Agency
    0.48
     Commission
    0.47
     district
    0.47
     enfans
    0.46
     Council
    0.45
     District
    0.44
    javax
    0.44
     Department
    0.44
     National
    0.43
     Fund
    0.43
    Activations Density 8.428%

    No Known Activations