© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4093
    Prev
    Next
    INDEX
    Explanations

    mentions of Universities and words indicating relations between institutions and people

    oai_token-act-pair · gemini-2.0-flash

    University/school

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الحره
    -0.75
    AnchorStyles
    -0.62
     INTERESAR
    -0.59
    BagLayout
    -0.54
    يميديا
    -0.52
    cherichia
    -0.51
     gynhyrchwyd
    -0.50
     بيها
    -0.50
     Occupations
    -0.50
    ulx
    -0.49
    POSITIVE LOGITS
     continúas
    0.61
    Parcelize
    0.60
    ValueStyle
    0.59
    BooleanField
    0.55
     Bowling
    0.49
     Ball
    0.49
    ItemBackground
    0.48
    Ball
    0.46
     boî
    0.46
    ExtendWith
    0.46
    Activations Density 2.319%

    No Known Activations