© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8960
    Prev
    Next
    INDEX
    Explanations

    words related to how other people are perceived

    oai_token-act-pair · gemini-2.0-flash

    strange/odd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     strange
    -2.11
     odd
    -1.95
     weird
    -1.86
    strange
    -1.84
    Strange
    -1.68
     strangest
    -1.64
     unusual
    -1.61
     Strange
    -1.60
    Weird
    -1.56
    weird
    -1.55
    POSITIVE LOGITS
    numerusform
    0.62
     respectivamente
    0.54
    horiz
    0.49
     Nugent
    0.48
     enro
    0.47
    Rote
    0.47
    respectively
    0.46
     OnInit
    0.46
     ruine
    0.46
     respectively
    0.45
    Activations Density 5.113%

    No Known Activations