© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    mentions of "Mad" in the context of TV shows or political movements

    oai_token-act-pair · gemini-2.0-flash

    instances of "Mad"

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

    Mad

    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
    Хьажоргаш
    -0.65
    IVEREF
    -0.60
     distanciation
    -0.59
    SequentialGroup
    -0.56
     Ender
    -0.55
    kuuta
    -0.54
     Савезне
    -0.54
    ❹
    -0.54
     основы
    -0.53
    Pull
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.48
    
    0.44
    SPJ
    0.43
    principalColumn
    0.42
     NSCoder
    0.42
    providedIn
    0.41
    getSimpleName
    0.41
    jupiter
    0.40
    inquirer
    0.40
     rubles
    0.40
    Activations Density 0.221%

    No Known Activations