© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7312
    Prev
    Next
    INDEX
    Explanations

    SQL code and legal documents.

    oai_token-act-pair · gemini-2.0-flash

    say "im" 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     im
    -2.42
     IM
    -2.33
     Im
    -2.30
    Im
    -2.22
     Imp
    -2.11
    Imp
    -2.03
    IM
    -1.92
     imp
    -1.88
     IMP
    -1.84
    Им
    -1.80
    POSITIVE LOGITS
    échelle
    0.48
    цездатний
    0.48
    ígenes
    0.45
     Sinai
    0.43
     Benson
    0.43
    Linha
    0.42
    vieja
    0.42
    écart
    0.41
    uxley
    0.41
    atherapy
    0.41
    Activations Density 1.337%

    No Known Activations