© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9912
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to chance, probability, and game playing

    oai_token-act-pair · gemini-2.0-flash

    words related to probability or games of chance

    np_token-act-pair-logits · gpt-4o-mini

    probability and letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    guenos
    -0.64
     Jefus
    -0.63
     Draws
    -0.61
    enderror
    -0.60
     Karab
    -0.59
    MockBean
    -0.58
    ssohn
    -0.57
     Etr
    -0.57
     Abbé
    -0.56
    Draws
    -0.56
    POSITIVE LOGITS
     GenerationType
    0.64
     six
    0.57
     Galbraith
    0.54
     PhpStorm
    0.51
     felt
    0.51
    tvguidetime
    0.50
     noDo
    0.48
    packung
    0.47
    OnDelete
    0.47
    pear
    0.46
    Activations Density 1.337%

    No Known Activations