© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7293
    Prev
    Next
    INDEX
    Explanations

    seemingly random numbers within surrounding text

    oai_token-act-pair · gemini-2.0-flash

    Political/economic/factual/medical discussion

    np_max-act-logits · gemini-2.0-flash

    ▁ Method used: 1. Reason: identical MAX_ACTIVATING_TOKENS

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    CloseOperation
    -0.56
    RTLE
    -0.55
    ïa
    -0.54
    MIDDLEWARE
    -0.49
    basicConfig
    -0.49
     UserDao
    -0.45
    دارد
    -0.45
    tdessen
    -0.43
    argout
    -0.43
     misschien
    -0.42
    POSITIVE LOGITS
    :✨
    0.71
     >=",
    0.60
     ujednoznacz
    0.59
    verwijspagina
    0.54
     Normdatei
    0.52
    ValueStyle
    0.52
     وتسجيلات
    0.51
     henvisninger
    0.50
     himſelf
    0.49
     Efq
    0.49
    Activations Density 2.068%

    No Known Activations