© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3704
    Prev
    Next
    INDEX
    Explanations

    words with a positive or negative conotation, usually adjectives

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ottima
    -0.47
     altrett
    -0.44
     élevées
    -0.42
     algum
    -0.41
     ciasc
    -0.40
     addirittura
    -0.40
     sufficiente
    -0.39
    thenReturn
    -0.39
    cluye
    -0.38
     awfully
    -0.38
    POSITIVE LOGITS
     оригіналу
    0.71
    ValueStyle
    0.65
    saraba
    0.65
    LookAnd
    0.60
    TypedDataSet
    0.60
    PerformLayout
    0.60
    IContainer
    0.59
    SourceChecksum
    0.56
    imea
    0.54
    MessageWindow
    0.51
    Activations Density 4.369%

    No Known Activations