© 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. 14846
    Prev
    Next
    INDEX
    Explanations

    forms of the word "want", words related to the pronoun "us", and the words them, people, see, know, take.

    oai_token-act-pair · gemini-2.0-flash

    to/que

    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
    UnitTesting
    -0.57
    LayoutStyle
    -0.57
     viewDidLoad
    -0.55
     EXISTS
    -0.52
    ciclopedia
    -0.51
     NgModule
    -0.51
     convertView
    -0.50
    ContentLoaded
    -0.50
     Khusus
    -0.46
     benzin
    -0.46
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.69
     lenker
    0.63
    toHaveBeenCalled
    0.60
    tvguidetime
    0.59
     Paglinawan
    0.59
     tartalomajánló
    0.58
    Instrumented
    0.57
     fubject
    0.56
     (_.
    0.56
     esternos
    0.56
    Activations Density 6.039%

    No Known Activations