© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    words related to geography, including rivers, mountains, and regions

    oai_token-act-pair · gemini-2.0-flash

    lakes and rivers

    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
     lakes
    -2.20
     lake
    -2.13
     Lake
    -2.13
    Lake
    -2.03
     LAKE
    -2.00
     Lakes
    -1.98
    lake
    -1.78
    LAKE
    -1.77
    Lakes
    -1.75
    lakes
    -1.73
    POSITIVE LOGITS
     démocr
    0.50
     تانيه
    0.47
    valentino
    0.47
    たって
    0.46
    iction
    0.46
    berton
    0.44
    Numerology
    0.43
     SEDS
    0.42
    Życiorys
    0.41
     Rupert
    0.41
    Activations Density 1.069%

    No Known Activations