© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6282
    Prev
    Next
    INDEX
    Explanations

    contractions with "not" or words containing "t" used to express negative sentiments of sorts

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    блица
    -0.48
     урна
    -0.46
     SqlParameter
    -0.45
    исленность
    -0.43
    ualaikum
    -0.42
     MessageBoxIcon
    -0.40
    varlak
    -0.40
    わけ
    -0.40
    Bioaccumulative
    -0.39
    weeper
    -0.39
    POSITIVE LOGITS
    ThroughAttribute
    0.74
    makeText
    0.68
    tableFuture
    0.68
    sizeCache
    0.62
    LookAnd
    0.60
     Савезне
    0.58
    IntentFilter
    0.58
    writeField
    0.57
     surla
    0.57
     []:
    0.57
    Activations Density 0.817%

    No Known Activations