© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8064
    Prev
    Next
    INDEX
    Explanations

    descriptions of spas and family holidays, including types of treatments and facilities

    oai_token-act-pair · 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
     Yoga
    -1.29
     yoga
    -1.27
     YOGA
    -1.23
    Yoga
    -1.19
    yoga
    -1.16
     spa
    -1.15
     Spa
    -1.05
    Spa
    -0.96
     yog
    -0.95
     Meditation
    -0.94
    POSITIVE LOGITS
    дравству
    0.54
    SourceChecksum
    0.53
    isAuthenticated
    0.52
    كلة
    0.51
     Palacios
    0.50
     Exacts
    0.49
    Muri
    0.48
    DataURL
    0.47
    rais
    0.47
     Chiu
    0.46
    Activations Density 2.047%

    No Known Activations