© 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. 8543
    Prev
    Next
    INDEX
    Explanations

    sentences which mention the word "I" or "you" speaking about preference and personal experience

    oai_token-act-pair · gemini-2.0-flash

    Expressing opinions and preferences

    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
     loved
    -1.05
     love
    -0.93
     Loved
    -0.91
     LOVED
    -0.81
     Love
    -0.81
    love
    -0.80
    loved
    -0.79
    Love
    -0.75
     loves
    -0.75
     LOVE
    -0.71
    POSITIVE LOGITS
    SceneManagement
    0.58
     defStyleAttr
    0.55
    出版年
    0.54
     Gae
    0.52
     Oto
    0.52
    verwijspagina
    0.52
     defStyle
    0.52
    Jit
    0.51
     发表于
    0.50
     Phry
    0.50
    Activations Density 6.216%

    No Known Activations