© 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. 4392
    Prev
    Next
    INDEX
    Explanations

    descriptors of temperature and weather

    oai_token-act-pair · gemini-2.0-flash

    Weather/temperature

    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
    URLException
    -0.82
    verwijspagina
    -0.71
     Normdatei
    -0.71
    קישורים
    -0.69
    ArgsConstructor
    -0.68
    RectangleBorder
    -0.67
     الدولى
    -0.66
     GenerationType
    -0.65
    ObjectContext
    -0.65
    audiovisuel
    -0.64
    POSITIVE LOGITS
    rike
    0.47
    nique
    0.45
     bal
    0.45
     dry
    0.45
     ni
    0.44
    arika
    0.44
    rid
    0.44
    ')[
    0.42
     below
    0.42
     fre
    0.41
    Activations Density 1.283%

    No Known Activations