© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    the names of Kyurangers, a fictional team of heroes

    oai_token-act-pair · gemini-2.0-flash

    Ky

    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
    Билгалдахарш
    -0.66
    badlogic
    -0.55
     "..\..\
    -0.54
    atoires
    -0.53
    icate
    -0.53
    icorn
    -0.52
    getDescriptor
    -0.52
    gorithm
    -0.51
    gods
    -0.50
    knex
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.67
     متعلقه
    0.65
     fumée
    0.54
     مشارکت‌کنندگان
    0.53
    ."));
    0.50
    !")
    0.49
     مشين
    0.48
    期刊论文
    0.47
     bezeichneter
    0.47
     يتيمه
    0.47
    Activations Density 1.634%

    No Known Activations