© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11143
    Prev
    Next
    INDEX
    Explanations

    contractions of "do not" and usage of the word "can", and somewhat usage of "want."

    oai_token-act-pair · gemini-2.0-flash

    say apostrophe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     '<?
    -0.53
    ')}}">
    -0.52
     છે
    -0.52
    IVING
    -0.51
    @[+][
    -0.51
    )))
    -0.50
    -0.50
     vik
    -0.50
     glab
    -0.50
     ''
    -0.49
    POSITIVE LOGITS
    AsUp
    0.65
     vectorielles
    0.59
     étoient
    0.57
     colorés
    0.56
     FetchType
    0.56
     stället
    0.56
     tartalomajánló
    0.56
     pauvres
    0.55
    Personensuche
    0.53
     nuages
    0.52
    Activations Density 2.127%
    No Known Activations