© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14458
    Prev
    Next
    INDEX
    Explanations

    blocks of code and certain numbers

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     pairwise
    -0.72
     between
    -0.68
     saling
    -0.57
    lasyon
    -0.56
     midpoint
    -0.55
    之间
    -0.55
     elkaar
    -0.54
    XMLSchema
    -0.54
    UpInside
    -0.54
     между
    -0.53
    POSITIVE LOGITS
    Билгалдахарш
    0.65
     Италијани
    0.62
     protoimpl
    0.57
    MigrationBuilder
    0.57
     Réponses
    0.54
    providedIn
    0.53
    évaluateur
    0.53
    
    0.53
    ьаж
    0.53
     kasarigan
    0.53
    Activations Density 2.559%

    No Known Activations