© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs such as "is", "are", "was" "were", when used with other verbs to express tense or mood.

    oai_token-act-pair · gemini-2.0-flash

    Verb usage

    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
    lillah
    -0.55
    limia
    -0.52
    TemporalType
    -0.50
    Unmarshaller
    -0.50
    ligator
    -0.48
    endela
    -0.48
    DEO
    -0.48
     Atlas
    -0.48
    olera
    -0.47
    adə
    -0.47
    POSITIVE LOGITS
     Meksiku
    0.58
     فريبيس
    0.53
    Composable
    0.53
    DllImport
    0.52
    发表于
    0.52
     confor
    0.47
    луй
    0.47
    UnusedPrivate
    0.47
    PageFactory
    0.46
    ollectionView
    0.44
    Activations Density 8.781%

    No Known Activations