© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14476
    Prev
    Next
    INDEX
    Explanations

    the names of administrative divisions in governments and schools

    oai_token-act-pair · gemini-2.0-flash

    school districts

    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
     district
    -2.66
     District
    -2.59
    District
    -2.52
     DISTRICT
    -2.41
    district
    -2.38
     districts
    -2.27
     Districts
    -2.23
    DISTRICT
    -2.09
    districts
    -1.95
     distrito
    -1.46
    POSITIVE LOGITS
     autorytatywna
    0.51
    ThroughAttribute
    0.51
    îtra
    0.49
     extérieures
    0.49
     "..\..\..\
    0.47
     Gesells
    0.46
     FormBuilder
    0.46
    PullParser
    0.43
     alene
    0.42
    acyjne
    0.42
    Activations Density 2.594%

    No Known Activations