© 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. 12477
    Prev
    Next
    INDEX
    Explanations

    instances of stating an ability plus the word "to".

    oai_token-act-pair · gemini-2.0-flash

    ability

    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
    CPtr
    -0.57
    Paola
    -0.54
    multer
    -0.53
    出版年
    -0.53
    恵
    -0.51
    PhysRev
    -0.51
     canadienne
    -0.50
     خارجية
    -0.50
    providedIn
    -0.49
     appartiennent
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.66
     ujednoznacz
    0.64
    IsContent
    0.63
     INTERESAR
    0.57
    Демографія
    0.57
     plan
    0.56
    AsUp
    0.54
     answer
    0.54
    ranean
    0.53
     master
    0.53
    Activations Density 1.087%

    No Known Activations