© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    passages that describe the distinctions or unique characteristics of different things

    oai_token-act-pair · gemini-2.0-flash

    uniqueness and differences

    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
     Jefus
    -0.96
    TagMode
    -0.93
     myſelf
    -0.90
     beginnetje
    -0.89
     propOrder
    -0.89
    ValueStyle
    -0.88
     houſe
    -0.88
     дописавши
    -0.85
     ***!
    -0.85
    новниш
    -0.84
    POSITIVE LOGITS
     
    0.43
     số
    0.39
    ்க
    0.39
     U
    0.38
     S
    0.37
     zákon
    0.37
     skj
    0.37
    ganta
    0.36
     O
    0.36
     (
    0.36
    Activations Density 0.423%

    No Known Activations