Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9576
    Prev
    Next
    INDEX
    Explanations

    text discussing the movement of people to cities

    oai_token-act-pair · gemini-2.0-flash

    cities

    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
     City
    -2.64
     city
    -2.42
    City
    -2.41
     CITY
    -2.36
    CITY
    -2.25
    city
    -2.23
     urban
    -2.16
     Urban
    -2.06
    Urban
    -1.98
    urban
    -1.84
    POSITIVE LOGITS
     Whigs
    0.49
    EDEFAULT
    0.48
    copyWith
    0.45
    ScopeManager
    0.45
    afio
    0.44
    olybden
    0.43
     firmware
    0.43
     hairline
    0.42
     senderismo
    0.41
     Langmuir
    0.41
    Activations Density 1.383%

    No Known Activations