© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14141
    Prev
    Next
    INDEX
    Explanations

    sentences that use a passive voice ("were/are [verb]") and other language related to historical events and the past

    oai_token-act-pair · gemini-2.0-flash

    professions ending in -ers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     kaynağından
    -0.49
    shund
    -0.47
    utnant
    -0.42
    SequentialGroup
    -0.40
    MergeFrom
    -0.40
    Nuorodos
    -0.40
     ***!
    -0.39
    zondere
    -0.39
    peteer
    -0.38
     disponibilités
    -0.38
    POSITIVE LOGITS
     scientists
    1.15
     engineers
    1.15
     skiers
    1.14
     dancers
    1.08
     researchers
    1.07
     athletes
    1.06
     hunters
    1.06
     designers
    1.05
     sailors
    1.05
     golfers
    1.05
    Activations Density 2.437%

    No Known Activations