© 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. 6764
    Prev
    Next
    INDEX
    Explanations

    terms associated with different kinds of fish and food preparation

    oai_token-act-pair · gemini-2.0-flash

    Seafood

    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
    komt
    -0.50
     garantías
    -0.46
     retrait
    -0.46
    helves
    -0.45
     löyty
    -0.45
    OrNil
    -0.45
    тельство
    -0.45
    Portale
    -0.44
    ء
    -0.44
    acyjna
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.78
     @"/
    0.73
     ***!
    0.67
    ніципа
    0.66
    OGND
    0.61
    NameInMap
    0.61
    UnusedPrivate
    0.60
    --)
    0.60
    Aiheesta
    0.59
    preduce
    0.59
    Activations Density 1.051%

    No Known Activations