© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3371
    Prev
    Next
    INDEX
    Explanations

    words related to subjective judgment of the quality or condition of some thing or entity

    oai_token-act-pair · gemini-2.0-flash

    best

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Personensuche
    -0.86
     HasFactory
    -0.82
    يكب
    -0.77
    Tikang
    -0.74
    uxxxx
    -0.73
     '\\;'
    -0.72
    webElementXpaths
    -0.71
    ValueGeneration
    -0.70
     nahilalakip
    -0.68
    exitRule
    -0.65
    POSITIVE LOGITS
     best
    2.70
    best
    2.41
    Best
    2.14
     Best
    2.02
     BEST
    1.78
    BEST
    1.70
     melhor
    1.48
     mejor
    1.42
     mejores
    1.36
     besten
    1.36
    Activations Density 5.515%

    No Known Activations