© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 242
    Prev
    Next
    INDEX
    Explanations

    a wide variety of things related to keeping, storing, and retaining something in a variety of topics.

    oai_token-act-pair · gemini-2.0-flash

    business and finance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     olvides
    -0.51
    ثيق
    -0.49
    rdı
    -0.48
     GENERATED
    -0.46
    seg
    -0.42
    VIAF
    -0.40
    下去
    -0.40
    Pautan
    -0.40
    ษ
    -0.40
    Forever
    -0.39
    POSITIVE LOGITS
    ]")]
    0.65
    ,:);
    0.64
    AnimationsModule
    0.63
    Koordinaten
    0.63
     disponibilités
    0.63
    المكان
    0.59
    ophyllum
    0.59
     NSCoder
    0.58
    RequiresApi
    0.58
    LookAnd
    0.58
    Activations Density 29.431%

    No Known Activations