© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16312
    Prev
    Next
    INDEX
    Explanations

    common words used to express negative sentiment related to difficult experiences

    oai_token-act-pair · gemini-2.0-flash

    archaic/foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    oredCriteria
    -0.54
    
    -0.51
     hä
    -0.49
    KEYCODE
    -0.48
    IconModule
    -0.47
    CloseOperation
    -0.45
    grà
    -0.44
    tagHelperRunner
    -0.44
    ICULO
    -0.44
    zinger
    -0.43
    POSITIVE LOGITS
     raiſ
    0.61
     auffi
    0.56
     chofe
    0.54
    ercises
    0.53
     Efq
    0.52
     tranſ
    0.52
     fubject
    0.51
     purpoſe
    0.50
     ſtand
    0.50
     reaſon
    0.49
    Activations Density 12.362%

    No Known Activations