© 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. 5814
    Prev
    Next
    INDEX
    Explanations

    sequences of unicode characters in devanagari script

    oai_token-act-pair · gemini-2.0-flash

    Hindu mantras and gods

    np_max-act-logits · gemini-2.0-flash
    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
    UnsafeEnabled
    -0.60
     متحده
    -0.56
    ThroughAttribute
    -0.54
     שוליים
    -0.53
     ويكيپيديا
    -0.52
     NUKAT
    -0.52
     ddelweddau
    -0.52
     TZ
    -0.51
     Italijanski
    -0.51
    
    -0.50
    POSITIVE LOGITS
    ṃ
    0.60
     vā
    0.56
    ṣ
    0.54
    ṁ
    0.51
    CodeAttribute
    0.50
    ṇ
    0.50
    Ṣ
    0.50
    adhy
    0.50
    attva
    0.49
    hā
    0.49
    Activations Density 7.410%

    No Known Activations