© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 994
    Prev
    Next
    INDEX
    Explanations

    mentions of suffering, horror, and economic issues as well as the word "the" and "daily"

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Atsauces
    -0.56
     الحره
    -0.53
     inevitable
    -0.53
     Challenging
    -0.51
     Uncertainty
    -0.50
     Dangers
    -0.50
     inevit
    -0.49
     influ
    -0.48
     skak
    -0.48
     harsh
    -0.48
    POSITIVE LOGITS
    enterOuterAlt
    0.62
    "]];
    0.60
    MessageState
    0.54
     BoxFit
    0.54
    #+#
    0.52
    utnik
    0.51
    CompleteListener
    0.50
    tså
    0.49
    ImageContext
    0.49
     imageNamed
    0.49
    Activations Density 3.219%

    No Known Activations