© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    prepositions and auxiliary verbs, especially those that imply a warning or something to avoid

    oai_token-act-pair · gemini-2.0-flash

    missing

    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
    TestingModule
    -0.71
    isContained
    -0.69
    CodedInputStream
    -0.68
    >",
    -0.58
     GenerationType
    -0.57
    ềm
    -0.57
     XCTest
    -0.56
    IVEREF
    -0.56
    typeorm
    -0.55
    NameInMap
    -0.54
    POSITIVE LOGITS
     missing
    2.48
    missing
    2.03
     Missing
    1.96
    Missing
    1.81
     MISSING
    1.77
    MISSING
    1.22
     fehl
    0.82
     lacking
    0.62
     absent
    0.58
     fehlt
    0.54
    Activations Density 5.806%

    No Known Activations