© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12836
    Prev
    Next
    INDEX
    Explanations

    the letters "ss" appearing somewhere in words

    oai_token-act-pair · gemini-2.0-flash

    ss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ss
    -2.30
    SS
    -1.95
     ss
    -1.55
     SS
    -1.55
    sss
    -1.28
    ssss
    -1.13
    sssss
    -1.06
    sses
    -1.01
    sso
    -0.99
    ssssssss
    -0.97
    POSITIVE LOGITS
     تضيفلها
    0.65
     nakalista
    0.64
     snippetHide
    0.61
     EconPapers
    0.58
    MENAFN
    0.57
    findpost
    0.56
     محفوظة
    0.53
    DMETHOD
    0.53
     OFDb
    0.52
    expandindo
    0.50
    Activations Density 0.808%

    No Known Activations