© 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. 12353
    Prev
    Next
    INDEX
    Explanations

    words relating to historic buildings on a university campus

    oai_token-act-pair · gemini-2.0-flash

    buildings and structures

    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
     building
    -1.36
    building
    -1.18
     Building
    -1.18
    Building
    -1.16
     BUILDING
    -1.09
    BUILDING
    -0.96
     edificio
    -0.83
     structure
    -0.76
     edifice
    -0.76
     facility
    -0.75
    POSITIVE LOGITS
    twimg
    0.67
    getKeyCode
    0.59
    utilisons
    0.58
    jenih
    0.56
     endforeach
    0.54
     riego
    0.54
     communiquez
    0.53
    kuuta
    0.52
    клопе
    0.51
    CppCodeGen
    0.51
    Activations Density 5.054%

    No Known Activations