© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    the topic of that article, focusing on river-related and monitoring words

    oai_token-act-pair · gemini-2.0-flash

    river

    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
     river
    -0.84
     RIVER
    -0.77
     River
    -0.74
    River
    -0.74
    river
    -0.64
    findpost
    -0.64
     Fluss
    -0.64
    yonel
    -0.63
     río
    -0.58
     rivers
    -0.56
    POSITIVE LOGITS
     ISLAND
    0.67
     Island
    0.59
     island
    0.59
    island
    0.56
    Island
    0.56
     eiland
    0.55
     Islander
    0.54
    Islands
    0.54
     Islanders
    0.52
     roads
    0.51
    Activations Density 8.104%

    No Known Activations