© 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. 6427
    Prev
    Next
    INDEX
    Explanations

    mentions of the US state Tennessee and its cities

    oai_token-act-pair · gemini-2.0-flash

    Tennessee locations and people

    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
     Tennessee
    -1.30
    Tennessee
    -1.25
     Memphis
    -1.22
     Nashville
    -1.22
     Ugandan
    -1.16
     Tenn
    -1.14
    Nashville
    -1.14
    Memphis
    -1.13
     Kentucky
    -1.09
     Bangladesh
    -1.09
    POSITIVE LOGITS
    ApiClient
    0.53
     tématu
    0.44
    ativement
    0.44
    dania
    0.43
     Athlete
    0.43
     Astrophysical
    0.43
     EClass
    0.43
     Alembic
    0.42
     gemeenten
    0.42
    ichio
    0.41
    Activations Density 1.811%

    No Known Activations