© 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. 8589
    Prev
    Next
    INDEX
    Explanations

    a mix of dialogue and combat.

    oai_token-act-pair · gemini-2.0-flash

    Sentence snippets

    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
     successfully
    -1.27
     achievement
    -1.23
    Achie
    -1.22
     achieving
    -1.20
     achieved
    -1.15
    successfully
    -1.14
     achieve
    -1.14
     Successfully
    -1.10
     achieves
    -1.09
     riusc
    -1.09
    POSITIVE LOGITS
    Rhestr
    0.58
    NewUrlParser
    0.57
    Executors
    0.55
    OptionsMenu
    0.55
     lateinit
    0.54
    PositiveButton
    0.54
    DispatchToProps
    0.54
    FlatList
    0.52
    zustellen
    0.52
    NegativeButton
    0.52
    Activations Density 3.612%

    No Known Activations