© 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. 12738
    Prev
    Next
    INDEX
    Explanations

    Spanish verbs and also some French verbs and the word "I" or "me".

    oai_token-act-pair · gemini-2.0-flash

    French phrases

    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
     given
    -0.52
     itſelf
    -0.52
     Tartar
    -0.49
    given
    -0.47
     errorCode
    -0.45
     Ebenezer
    -0.44
     seen
    -0.44
     Efe
    -0.44
     the
    -0.43
     Uchiha
    -0.43
    POSITIVE LOGITS
     виправивши
    0.84
     समीक्षाओं
    0.81
     كومونز
    0.80
    AndEndTag
    0.75
     EconPapers
    0.73
     &___
    0.69
    __":
    0.69
    setVerticalGroup
    0.68
     surla
    0.68
     defaultstate
    0.67
    Activations Density 0.255%

    No Known Activations