© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3985
    Prev
    Next
    INDEX
    Explanations

    proper nouns with multiple parts (names, places)

    oai_token-act-pair · gemini-2.0-flash

    Spanish surnames

    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
     الحره
    -0.62
    AnimationsModule
    -0.57
     Shakspeare
    -0.54
     يتيمه
    -0.54
     للاسماء
    -0.53
     Odysseus
    -0.53
     ddelweddau
    -0.51
     beginnetje
    -0.51
     InputDecoration
    -0.49
     daewoo
    -0.48
    POSITIVE LOGITS
     Gutiérrez
    0.59
     Domínguez
    0.58
     Núñez
    0.56
     Méndez
    0.55
     Valdés
    0.52
     Pacheco
    0.51
     Jiménez
    0.50
     López
    0.50
     Barrios
    0.50
    abstractmethod
    0.49
    Activations Density 3.910%

    No Known Activations