© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14845
    Prev
    Next
    INDEX
    Explanations

    possessive words

    oai_token-act-pair · gemini-2.0-flash

    s

    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
     procedente
    -0.58
     pluie
    -0.55
    <bos>
    -0.50
     eccl
    -0.50
     kerül
    -0.49
     noël
    -0.48
     suelo
    -0.48
    copyOf
    -0.46
    Quiz
    -0.46
     tomber
    -0.45
    POSITIVE LOGITS
    ViewFeatures
    0.74
    kuuta
    0.66
    enumi
    0.65
    PreferredItem
    0.64
     onCreateView
    0.61
     الاطلاع
    0.60
    StoryboardSegue
    0.60
    MigrationBuilder
    0.59
     own
    0.58
    Nationalité
    0.56
    Activations Density 1.501%

    No Known Activations