© 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. 14803
    Prev
    Next
    INDEX
    Explanations

    punctuation at the end of sentences, especially exclamation points in quotes

    oai_token-act-pair · gemini-2.0-flash

    Non-English 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
    CrossRef
    -0.69
     MenuView
    -0.64
    nonatomic
    -0.58
     Our
    -0.54
    AndEndTag
    -0.54
    AlterField
    -0.51
     InputDecoration
    -0.51
    oris
    -0.49
     considering
    -0.49
    :+:
    -0.49
    POSITIVE LOGITS
     referenties
    0.76
    ंदीखरीदारी
    0.73
     spéciales
    0.56
     мәкал
    0.54
     AppCompatTheme
    0.51
    VersionUID
    0.50
    Iné
    0.50
    évaluateur
    0.49
     bewer
    0.49
    存于互联网档案馆
    0.48
    Activations Density 7.439%

    No Known Activations