© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11356
    Prev
    Next
    INDEX
    Explanations

    different types of food

    oai_token-act-pair · gemini-2.0-flash

    food items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.50
     fast
    -0.47
    hamburger
    -0.46
     Baillargeon
    -0.45
    🍔
    -0.43
     or
    -0.43
     about
    -0.42
    qvist
    -0.42
    memset
    -0.42
    INSIDE
    -0.42
    POSITIVE LOGITS
    TagMode
    0.88
    ReusableCell
    0.83
    Tikang
    0.76
     Theſe
    0.76
    providedIn
    0.71
     kasarigan
    0.71
     Efq
    0.71
     ſtate
    0.69
     ―――――
    0.69
     raiſ
    0.68
    Activations Density 0.998%

    No Known Activations