Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12206
    Prev
    Next
    INDEX
    Explanations

    the word "so" followed closely by the word "what" or the pronoun "I" or but

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     nî
    -0.63
    <bos>
    -0.50
    ControllerAdvice
    -0.49
    
    -0.49
     stanovnika
    -0.47
     firebaseConfig
    -0.47
    Xna
    -0.46
    日閲覧
    -0.46
    getMinutes
    -0.45
    Bronnen
    -0.44
    POSITIVE LOGITS
    الحياه
    0.66
    aguas
    0.56
    vezet
    0.51
    subpackage
    0.51
    bitField
    0.50
    ^(@)
    0.50
    İM
    0.50
    iotensin
    0.50
    sunter
    0.50
    ,:),
    0.49
    Activations Density 0.128%

    No Known Activations