© 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. 6102
    Prev
    Next
    INDEX
    Explanations

    words and phrases to describe the quality or characteristics of something.

    oai_token-act-pair · gemini-2.0-flash

    class

    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
     tartalomajánló
    -0.59
     habet
    -0.58
    gouv
    -0.58
    wiſe
    -0.56
    createNewFile
    -0.54
     Profitez
    -0.54
     themſelves
    -0.53
     reCAPTCHA
    -0.53
    CloseOperation
    -0.53
    ]='\
    -0.53
    POSITIVE LOGITS
     class
    2.48
    class
    2.00
     Class
    1.81
     classe
    1.77
     CLASS
    1.68
     clase
    1.66
    Class
    1.63
     Klasse
    1.46
     classes
    1.39
    CLASS
    1.38
    Activations Density 0.989%

    No Known Activations