© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15316
    Prev
    Next
    INDEX
    Explanations

    blocks of Japanese text expressing confusion and asking for help with a programming problem

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
    Negative Logits
    itinéraire
    -0.49
    URLException
    -0.43
     Normdatei
    -0.43
    ніципалі
    -0.41
    存于互联网档案馆
    -0.40
     كومونز
    -0.40
     linkovi
    -0.38
     estekak
    -0.37
     continúas
    -0.36
     magasiner
    -0.36
    POSITIVE LOGITS
     feroit
    0.68
     auroit
    0.64
     neutre
    0.63
     medži
    0.62
     vandens
    0.61
     étoit
    0.60
     pouvoit
    0.60
     mauva
    0.60
     aukš
    0.59
     virš
    0.59
    Activations Density 0.255%

    No Known Activations