© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1979
    Prev
    Next
    INDEX
    Explanations

    noun phrases or sentence fragments that contain articles, prepositions, and adjectives

    oai_token-act-pair · gemini-2.0-flash

    Length or duration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nakalista
    -1.16
     >=",
    -1.05
    RegistryLite
    -1.04
     <=",
    -1.02
     lenker
    -0.98
    ьаж
    -0.98
    WithIOException
    -0.97
    LookAnd
    -0.96
    ніципалі
    -0.96
    ///</
    -0.94
    POSITIVE LOGITS
     length
    1.09
    Length
    0.82
    length
    0.82
     LENGTH
    0.79
     Length
    0.78
    LENGTH
    0.67
     duration
    0.58
     complete
    0.56
     given
    0.54
    ength
    0.54
    Activations Density 4.029%

    No Known Activations