© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14647
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the Hindu deity Narasimha and related religious practices.

    oai_token-act-pair · gemini-2.0-flash

    Archaic words

    np_max-act-logits · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     /\.
    -0.34
     nationaux
    -0.33
     yoktur
    -0.31
    MultipartFile
    -0.30
     ferons
    -0.29
     voulons
    -0.29
     pokoj
    -0.28
    HttpClientModule
    -0.27
    vikle
    -0.27
     distribuidor
    -0.27
    POSITIVE LOGITS
     myſelf
    0.84
    ഔ
    0.76
    ſelves
    0.75
     Roskov
    0.75
     Efq
    0.74
     Diſ
    0.74
     Monfieur
    0.74
     Perſ
    0.73
     themſelves
    0.73
     ſy
    0.72
    Activations Density 6.775%

    No Known Activations