© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    Japanese sentences expressing uncertainty and a request for help with a technical issue

    oai_token-act-pair · gemini-2.0-flash

    Mixed languages and contexts

    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
     متعلقه
    -1.00
    AnchorStyles
    -0.88
     estekak
    -0.85
     CreateTagHelper
    -0.81
    thâu
    -0.79
     JpaRepository
    -0.77
     resourceCulture
    -0.73
     nahilalakip
    -0.71
    AndEndTag
    -0.71
     AssemblyCulture
    -0.71
    POSITIVE LOGITS
     secteurs
    0.30
     itp
    0.28
     impossibile
    0.28
    Yann
    0.27
     défis
    0.26
     diarias
    0.26
     Griechen
    0.26
     lhe
    0.26
     Gef
    0.26
     visão
    0.25
    Activations Density 0.353%

    No Known Activations