© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11354
    Prev
    Next
    INDEX
    Explanations

    the substring "ess", words ending in "ing", words "somehow", "maybe", and words bigger than usual

    oai_token-act-pair · gemini-2.0-flash

    ess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    %)$
    -0.88
    yntaxException
    -0.78
     different
    -0.78
    хьтан
    -0.77
     Bourgoin
    -0.75
    ropshire
    -0.74
    EDEFAULT
    -0.73
    otka
    -0.73
    antaine
    -0.73
    phinx
    -0.72
    POSITIVE LOGITS
     titolata
    0.92
     picioare
    0.85
     vectorielles
    0.84
     pericolo
    0.78
     dubbio
    0.77
    bbene
    0.77
     feroit
    0.77
     scattata
    0.74
     giù
    0.73
     poichè
    0.72
    Activations Density 2.062%

    No Known Activations