© 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. 371
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" with some surrounding context.

    oai_token-act-pair · gemini-2.0-flash

    foreign 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
    InputTagHelper
    -0.71
    __':
    -0.67
    Hentet
    -0.65
    TagMode
    -0.63
    prüche
    -0.57
    __":
    -0.57
    TagHelper
    -0.56
    BagConstraints
    -0.55
     poor
    -0.55
    Przypisy
    -0.55
    POSITIVE LOGITS
    Diweddarwch
    0.57
    Демографія
    0.53
    setta
    0.52
     anzunehmen
    0.51
     zru
    0.49
    ыгана
    0.49
    encodeWith
    0.49
     henvisninger
    0.48
    esez
    0.46
    bigsqcup
    0.45
    Activations Density 5.258%

    No Known Activations