© 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. 9185
    Prev
    Next
    INDEX
    Explanations

    words related to alcohol and drinking

    oai_token-act-pair · gemini-2.0-flash

    uncommon drink-related terms

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

    usually

    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
     Bourgoin
    -0.82
    脚注の使い方
    -0.75
    +#+#
    -0.74
     فريبيس
    -0.69
     jScrollPane
    -0.67
    Bibliograf
    -0.64
     gynhyrchwyd
    -0.64
    adaptiveStyles
    -0.63
    стви
    -0.63
     kenzo
    -0.62
    POSITIVE LOGITS
    eqn
    0.47
    utable
    0.44
     radiador
    0.42
    BASEPATH
    0.40
     baseman
    0.40
    ieder
    0.38
     δη
    0.38
     gez
    0.38
    пуск
    0.37
    putan
    0.37
    Activations Density 0.588%

    No Known Activations