© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15864
    Prev
    Next
    INDEX
    Explanations

    variations of "I am", "we are", or "they are", along with words such as delighted, grateful, or proud

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment

    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
     eager
    -0.63
     try
    -0.63
     glad
    -0.60
    AndEndTag
    -0.59
     excited
    -0.59
    Excited
    -0.59
     Interested
    -0.58
     interested
    -0.57
     Excited
    -0.57
    EDEFAULT
    -0.56
    POSITIVE LOGITS
    __":
    0.55
    ]='\
    0.55
     nivå
    0.52
     متعلقه
    0.52
    CodedInputStream
    0.51
    __.__
    0.51
    UserScript
    0.51
    __':
    0.51
     composants
    0.48
    ￡
    0.48
    Activations Density 4.150%

    No Known Activations