© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12384
    Prev
    Next
    INDEX
    Explanations

    recipes with beer

    oai_token-act-pair · gemini-2.0-flash

    beer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    таратура
    -0.44
     Վերցված
    -0.42
    xase
    -0.42
    MigrationBuilder
    -0.41
     pat
    -0.40
     مشين
    -0.40
     Mar
    -0.40
     fossa
    -0.39
    byr
    -0.38
    المناصب
    -0.37
    POSITIVE LOGITS
    BASEPATH
    0.66
    MethodManager
    0.62
     parseFrom
    0.58
    thâu
    0.56
    ."]
    0.56
    Portale
    0.56
    IVEREF
    0.56
    }();
    0.56
    complexContent
    0.55
    
    0.55
    Activations Density 2.775%

    No Known Activations