© 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. 5882
    Prev
    Next
    INDEX
    Explanations

    personal pronouns in political text.

    oai_token-act-pair · gemini-2.0-flash

    Speculation using "if"

    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
    odeon
    -0.65
     not
    -0.61
     propOrder
    -0.57
    AddField
    -0.57
     DbType
    -0.56
     BoxFit
    -0.53
    PointerException
    -0.53
     Not
    -0.52
    ölker
    -0.52
    BagConstraints
    -0.52
    POSITIVE LOGITS
     ever
    0.84
     are
    0.81
    ever
    0.69
    Are
    0.65
     ARE
    0.65
     EVER
    0.64
    \}\\
    0.64
    are
    0.64
     Are
    0.61
    Ever
    0.60
    Activations Density 19.096%

    No Known Activations