© 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. 4246
    Prev
    Next
    INDEX
    Explanations

    measurements or descriptions of scientific laboratory conditions

    oai_token-act-pair · gemini-2.0-flash

    say water words

    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
     Water
    -2.81
    Water
    -2.77
     water
    -2.77
     WATER
    -2.58
    water
    -2.58
    WATER
    -2.47
     Wasser
    -2.20
     waters
    -2.17
     Вода
    -2.08
    Wasser
    -2.05
    POSITIVE LOGITS
    ษัท
    0.58
     ddelweddau
    0.55
    RRect
    0.48
    nall
    0.47
    τουργ
    0.47
     muualla
    0.46
    cinnati
    0.45
    الحياه
    0.44
     régiment
    0.44
     Bless
    0.43
    Activations Density 1.886%

    No Known Activations