© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    text about air conditioning and refrigeration systems

    oai_token-act-pair · gemini-2.0-flash

    air conditioning systems

    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
     Normdatei
    -0.71
    HasForeignKey
    -0.65
     beginnetje
    -0.63
     Roskov
    -0.61
    Air
    -0.59
     Air
    -0.58
     jadx
    -0.58
    queryInterface
    -0.57
     Signalez
    -0.57
    IUrlHelper
    -0.57
    POSITIVE LOGITS
     outdoor
    0.56
    .")]
    0.54
    )"),
    0.54
    onnage
    0.53
    ?>">
    0.52
    outdoor
    0.51
     تانيه
    0.50
    %)$
    0.50
    ņš
    0.47
    iteracy
    0.47
    Activations Density 0.815%

    No Known Activations