© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    descriptions of rooms in a residence, including the presence of adjectives describing size

    oai_token-act-pair · gemini-2.0-flash

    rooms in a house

    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
     चुनें
    -0.39
     el
    -0.36
    Bindings
    -0.36
    вен
    -0.35
     col
    -0.35
     scal
    -0.35
    sele
    -0.34
     {
    -0.34
     man
    -0.34
     
    -0.34
    POSITIVE LOGITS
     Normdatei
    0.99
     FetchType
    0.95
    IntoConstraints
    0.94
     Италијани
    0.89
    tvguidetime
    0.87
    )");
    0.82
    +#+#
    0.82
     Formal
    0.81
     resourceCulture
    0.80
    ScopeManager
    0.80
    Activations Density 0.626%

    No Known Activations