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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11276
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Hindu worship practices, particularly those involving purity and discipline

    oai_token-act-pair · gemini-2.0-flash

    mixed language terms or references

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

    Abstract concepts

    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
    __":
    
    -0.56
     TextInputType
    -0.55
    __":
    -0.47
    ::::::::
    -0.47
    Portale
    -0.47
     payé
    -0.46
    出错
    -0.45
     Glaser
    -0.44
     createSprite
    -0.43
    Personendaten
    -0.43
    POSITIVE LOGITS
    Kaynakça
    0.58
    SourceChecksum
    0.53
    rrggbb
    0.53
    pozycji
    0.52
    rhosis
    0.52
    pity
    0.51
    СТВО
    0.51
     pity
    0.51
    fileID
    0.50
     nahilalakip
    0.49
    Activations Density 1.262%

    No Known Activations