© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1344
    Prev
    Next
    INDEX
    Explanations

    a variety of words with no clear unifying characteristic, although many are adjectives or adverbs with a slight negative connation such as pale and numerous.

    oai_token-act-pair · gemini-2.0-flash

    significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     gynhyrchwyd
    -0.45
     result
    -0.45
     be
    -0.44
     bein
    -0.43
     contain
    -0.43
    тал
    -0.42
     internetowa
    -0.42
    caden
    -0.41
    ...
    -0.40
    Sim
    -0.40
    POSITIVE LOGITS
     pleaſure
    0.75
     мәкал
    0.75
     Савезне
    0.73
     himſelf
    0.73
     ſmall
    0.71
     preſent
    0.70
     myſelf
    0.70
     Monfieur
    0.70
     poffe
    0.70
    éez
    0.69
    Activations Density 7.307%

    No Known Activations