© 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. 12248
    Prev
    Next
    INDEX
    Explanations

    activation clusters appearing in Spanish, Italian, and Portuguese

    oai_token-act-pair · gemini-2.0-flash

    e

    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
    ConstraintMaker
    -0.72
     فريبيس
    -0.68
     незавершена
    -0.66
     ✭✭
    -0.62
     internetowa
    -0.59
    Personensuche
    -0.56
     autorytatywna
    -0.55
    +#+#
    -0.55
    InjectAttribute
    -0.55
     GetEnumerator
    -0.55
    POSITIVE LOGITS
    offie
    0.61
    zugehen
    0.54
    ływ
    0.53
    awaiter
    0.50
    ++
    0.48
     Scotia
    0.47
     Hock
    0.46
    styleUrls
    0.46
    ++);
    0.45
    ]^{-
    0.44
    Activations Density 0.356%

    No Known Activations