© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12139
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and pronouns relating to 'people' or 'group'

    oai_token-act-pair · gemini-2.0-flash

    terms related to government and authority

    np_token-act-pair-logits · gpt-4o-mini

    expressing opinions

    np_max-act-logits · gemini-2.0-flash
    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
     GenerationType
    -0.71
     AssemblyProduct
    -0.60
    cshtml
    -0.55
    MethodManager
    -0.53
    ]:
    -0.52
     betweenstory
    -0.50
    ✭✭
    -0.49
     linkovi
    -0.47
     nonatomic
    -0.47
    WebElementEntity
    -0.47
    POSITIVE LOGITS
     Draws
    0.59
    draws
    0.59
     expressing
    0.58
     sprend
    0.58
     expresses
    0.57
     draw
    0.56
    ostock
    0.55
     draws
    0.54
     describe
    0.53
    dotte
    0.52
    Activations Density 4.066%

    No Known Activations