© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3002
    Prev
    Next
    INDEX
    Explanations

    words related to coding or illegal acts

    oai_token-act-pair · gemini-2.0-flash

    take

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IUrlHelper
    -0.65
    
    -0.63
     متعلقه
    -0.61
     "..\..\
    -0.59
     Roskov
    -0.57
    TableHead
    -0.56
     ujednoznacz
    -0.55
    ragalactic
    -0.54
     BigNumberish
    -0.54
    Personensuche
    -0.52
    POSITIVE LOGITS
     taking
    1.64
     takes
    1.59
     take
    1.59
    Taking
    1.57
    taking
    1.57
     Taking
    1.56
    Take
    1.50
    take
    1.49
     Takes
    1.48
    takes
    1.48
    Activations Density 4.231%

    No Known Activations