© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14547
    Prev
    Next
    INDEX
    Explanations

    words and phrases that end in "ize", plus some related prefixes and suffixes

    oai_token-act-pair · gemini-2.0-flash

    say "z" ending words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     دیکھیے
    -0.75
    Şi
    -0.71
    ⓧ
    -0.70
     minim
    -0.69
     crystall
    -0.66
     visual
    -0.65
     getItemCount
    -0.64
     custom
    -0.64
     programme
    -0.63
     Programme
    -0.63
    POSITIVE LOGITS
    Organizations
    1.09
     Ее
    1.08
     Еще
    1.02
    Organizational
    1.02
    organizations
    1.02
     organizations
    1.02
    organizational
    1.02
     organizational
    0.99
     realize
    0.96
     finalize
    0.96
    Activations Density 8.342%

    No Known Activations