© 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. 8956
    Prev
    Next
    INDEX
    Explanations

    the word "the" and nearby words

    oai_token-act-pair · gemini-2.0-flash

    fall

    np_max-act-logits · gemini-2.0-flash

    say "fall"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Sommer
    -0.93
    GEBURTSDATUM
    -0.83
    Sommer
    -0.81
    Summer
    -0.81
    SUMMER
    -0.77
    summer
    -0.76
     summer
    -0.75
     SUMMER
    -0.74
     Summer
    -0.71
     winter
    -0.71
    POSITIVE LOGITS
     fall
    2.84
    fall
    2.34
    Fall
    2.25
     Fall
    2.25
     FALL
    2.08
    FALL
    1.92
     falls
    1.88
    falls
    1.64
     Falls
    1.40
     falling
    1.38
    Activations Density 8.005%

    No Known Activations