© 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. 6872
    Prev
    Next
    INDEX
    Explanations

    first and third person pronouns and associated verbs

    oai_token-act-pair · gemini-2.0-flash

    narrative story

    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
    verwijspagina
    -0.65
     propOrder
    -0.64
     ویکی‌پدیای
    -0.57
    RegressionTest
    -0.56
    CloseOperation
    -0.56
     styr
    -0.55
     setuptools
    -0.55
    ThemeOverlay
    -0.55
    windowFixed
    -0.54
     encontraban
    -0.53
    POSITIVE LOGITS
     discovering
    0.57
     watching
    0.54
     taking
    0.54
     seeing
    0.53
     walking
    0.52
     taste
    0.51
     singing
    0.51
     reacting
    0.50
     driving
    0.50
     spinning
    0.50
    Activations Density 9.647%

    No Known Activations