© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9709
    Prev
    Next
    INDEX
    Explanations

    words describing story elements, plot, and emotional reactions related to movies

    oai_token-act-pair · gemini-2.0-flash

    movie reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Numerade
    -0.48
    Marshaller
    -0.45
    tonsoft
    -0.44
    γ
    -0.44
    WriteHeader
    -0.42
    mainAxisSize
    -0.42
    lares
    -0.41
    kunta
    -0.40
     γ
    -0.40
     cil
    -0.39
    POSITIVE LOGITS
    UnsafeEnabled
    0.91
    PerformLayout
    0.84
    دانشنامهٔ
    0.78
    WithIOException
    0.76
     चीज़ों
    0.73
    MLLoader
    0.68
    رشف
    0.68
    omitempty
    0.65
    kloped
    0.64
     <<<<<<<<<<<<<<
    0.63
    Activations Density 7.639%

    No Known Activations