© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12148
    Prev
    Next
    INDEX
    Explanations

    question asking and opinion-expressing constructions using "is", "are", "do", "think", "or", "what", "kind", "true"

    oai_token-act-pair · gemini-2.0-flash

    discussions

    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
     demander
    -0.45
     range
    -0.43
    tellen
    -0.43
     co
    -0.43
    сован
    -0.41
     window
    -0.40
     me
    -0.40
     Kelly
    -0.40
    லை
    -0.40
    ner
    -0.39
    POSITIVE LOGITS
     PLWABN
    0.84
    Personendaten
    0.83
    SharedCtor
    0.83
    __':
    
    0.81
    AndEndTag
    0.78
    setVerticalGroup
    0.77
     Assyrian
    0.77
    httphttps
    0.74
    ftagPool
    0.74
    ApiProperty
    0.73
    Activations Density 0.254%

    No Known Activations