© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7605
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to awards and honors given to people especially in academic settings.

    oai_token-act-pair · gemini-2.0-flash

    awards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     myſelf
    -0.75
     Efq
    -0.73
     raiſ
    -0.72
     itſelf
    -0.69
    Smarty
    -0.68
     ISNI
    -0.68
     pleaſure
    -0.67
     ſche
    -0.66
     juſ
    -0.66
     themſelves
    -0.66
    POSITIVE LOGITS
    Vidite
    0.58
    veen
    0.49
    umenter
    0.49
    otsu
    0.48
    raging
    0.48
    prite
    0.48
    setzungen
    0.48
    afat
    0.47
    ocere
    0.47
     TestBed
    0.47
    Activations Density 12.653%

    No Known Activations