© 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. 383
    Prev
    Next
    INDEX
    Explanations

    places with specific suffixes, and potentially proper nouns, especially those related to Eastern Europe and WWII.

    oai_token-act-pair · gemini-2.0-flash

    Eastern European places

    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
    MigrationBuilder
    -0.79
     تضيفلها
    -0.76
    ValueStyle
    -0.66
    featureID
    -0.65
     فريبيس
    -0.65
    GraphicsUnit
    -0.65
     <=",
    -0.63
    writeFieldEnd
    -0.63
     Normdatei
    -0.62
     للمعارف
    -0.57
    POSITIVE LOGITS
    skaya
    0.54
    ć
    0.51
    Ć
    0.50
     Vlas
    0.50
     Pavel
    0.50
    ov
    0.49
    ska
    0.49
     Ż
    0.48
     Ž
    0.48
    ski
    0.48
    Activations Density 25.924%

    No Known Activations