© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1743
    Prev
    Next
    INDEX
    Explanations

    words and context related to the use of verbs, and to language with active subjects doing things.

    oai_token-act-pair · gemini-2.0-flash

    actions and states of being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     autrement
    -0.49
     quelconque
    -0.46
     Recently
    -0.46
     recientemente
    -0.46
     ostat
    -0.45
     recently
    -0.45
     недавно
    -0.44
    ///</
    -0.44
    fattning
    -0.44
    redning
    -0.43
    POSITIVE LOGITS
     AssemblyVersion
    0.93
     оригіналу
    0.81
    uxxxx
    0.77
     typelib
    0.77
    DockStyle
    0.76
     ContentValues
    0.76
    ########.
    0.75
    AsUp
    0.71
     كومونز
    0.71
    didSet
    0.71
    Activations Density 11.598%

    No Known Activations