© 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. 4515
    Prev
    Next
    INDEX
    Explanations

    words pertaining to theories, opinions or established facts

    oai_token-act-pair · gemini-2.0-flash

    theory

    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
     للاسماء
    -0.62
    Eksterne
    -0.58
     BaseActivity
    -0.55
    Chham
    -0.53
     précédents
    -0.50
     alimentaires
    -0.50
    انيف
    -0.50
     inför
    -0.48
     ägg
    -0.48
     pitié
    -0.47
    POSITIVE LOGITS
    UnknownFieldSet
    0.59
    complexType
    0.54
     called
    0.51
    uerre
    0.51
     defaultstate
    0.50
    Распо
    0.50
     Rab
    0.49
    sidemargin
    0.49
     pos
    0.49
    present
    0.49
    Activations Density 7.517%

    No Known Activations