Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7222
    Prev
    Next
    INDEX
    Explanations

    extremely common words like "the", "a", "in", "it", "my", and "that" and the word "something"

    oai_token-act-pair · gemini-2.0-flash

    something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ſche
    -2.45
     pleaſure
    -2.36
     purpoſe
    -2.30
     Monfieur
    -2.28
     Cæsar
    -2.17
     quæ
    -2.17
     Majefty
    -2.16
     itſelf
    -2.13
     Diſ
    -2.09
     ſever
    -2.09
    POSITIVE LOGITS
    ratulations
    2.17
    "):
    
    1.96
    — 
    1.87
    '):
    
    1.86
    æus
    1.84
    ')):
    1.83
    ficulty
    1.81
    iffance
    1.80
    polation
    1.80
    "])
    
    1.77
    Activations Density 6.289%

    No Known Activations