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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12603
    Prev
    Next
    INDEX
    Explanations

    the city of "Los Angeles", and other place names, along with the word "Prior"

    oai_token-act-pair · gemini-2.0-flash

    Los

    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
    ctu
    -0.54
    цездатний
    -0.53
    ])):
    -0.50
    (__('
    -0.49
    InputBorder
    -0.48
    queryInterface
    -0.47
    jsonwebtoken
    -0.47
     SqlConnection
    -0.46
    :✨
    -0.46
    ICP
    -0.46
    POSITIVE LOGITS
    šanai
    0.59
    Примітки
    0.58
     sahiptir
    0.56
    hofer
    0.56
     pauvres
    0.54
     nélkül
    0.53
     détru
    0.53
     juridiques
    0.52
     présidenti
    0.52
     szolg
    0.52
    Activations Density 5.680%

    No Known Activations