© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    the word "perfect" and related words like "ideal".

    oai_token-act-pair · gemini-2.0-flash

    perfect ideal

    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
     perfect
    -2.91
    perfect
    -2.83
    Perfect
    -2.75
     Perfect
    -2.72
     ideal
    -2.58
    Ideal
    -2.56
     Ideal
    -2.50
     PERFECT
    -2.50
    ideal
    -2.44
     IDEAL
    -2.23
    POSITIVE LOGITS
    yarnpkg
    0.52
     שוליים
    0.49
    หวัด
    0.45
    NavController
    0.45
     Majesté
    0.44
     Combien
    0.44
     Boc
    0.44
     utafitiHapana
    0.44
     gepubliceerd
    0.42
    NewUrlParser
    0.42
    Activations Density 1.920%

    No Known Activations