© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12731
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to negative emotions

    oai_token-act-pair · gemini-2.0-flash

    Sofia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    viewBox
    -0.48
    RenderAtEndOf
    -0.48
     SwitchCompat
    -0.46
     A
    -0.44
    ыгана
    -0.42
     most
    -0.42
     svar
    -0.42
     ảo
    -0.41
     reparti
    -0.41
     Mor
    -0.40
    POSITIVE LOGITS
    Bronnen
    0.70
     كومونز
    0.67
    ViewInit
    0.64
     kasarigan
    0.63
     Epistle
    0.63
    WEBPACK
    0.61
    basicConfig
    0.60
    ponses
    0.59
     []:
    0.59
     Tamp
    0.57
    Activations Density 7.342%

    No Known Activations