© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    the first two letters of the word "enumerate" and the prefix "en" as it is used to start multiple words.

    oai_token-act-pair · gemini-2.0-flash

    programming/legal terms

    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
    évaluateur
    -0.70
    DotNetBar
    -0.65
     gynhyrchwyd
    -0.64
     TestBed
    -0.61
    StoryboardSegue
    -0.61
    SharedDtor
    -0.61
    rungsseite
    -0.60
    Abitanti
    -0.60
    SourceChecksum
    -0.60
    WebElementEntity
    -0.54
    POSITIVE LOGITS
    se
    0.58
    URLException
    0.51
    Hozzáférés
    0.51
    ro
    0.50
    FetchType
    0.48
    jednoc
    0.47
    tų
    0.47
     StatelessWidget
    0.44
     schu
    0.43
    cellaneous
    0.42
    Activations Density 2.840%

    No Known Activations