© 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. 14867
    Prev
    Next
    INDEX
    Explanations

    what appears to be the start of a casual, personal, supportive message

    oai_token-act-pair · 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
    ⓧ
    -0.68
    Datuak
    -0.67
     ***!
    -0.65
    AddTagHelper
    -0.63
    цезда
    -0.61
     jadx
    -0.60
    kháu
    -0.60
    CodeAttribute
    -0.60
     geslacht
    -0.58
    WriteLiteral
    -0.58
    POSITIVE LOGITS
     themſelves
    0.51
     Приступљено
    0.50
     himſelf
    0.50
     ſmall
    0.48
     Houſe
    0.48
     greateſt
    0.47
     neceſſ
    0.46
    FunctionFlags
    0.46
     houſe
    0.46
     neceffary
    0.45
    Activations Density 30.558%

    No Known Activations