© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14758
    Prev
    Next
    INDEX
    Explanations

    a mishmash of function words and sentiment words.

    oai_token-act-pair · gemini-2.0-flash

    perfect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.89
     nahilalakip
    -0.65
     Roskov
    -0.61
    دانشنامهٔ
    -0.61
    InputBorder
    -0.54
     rând
    -0.53
     tremp
    -0.52
     huvud
    -0.49
     مرئيه
    -0.48
     chiaramente
    -0.48
    POSITIVE LOGITS
     perfect
    2.67
    perfect
    2.48
     Perfect
    2.19
    Perfect
    2.17
     PERFECT
    1.96
    PERFECT
    1.80
     perfecto
    1.74
     perfectos
    1.73
     perfecta
    1.71
     perfetto
    1.64
    Activations Density 4.130%

    No Known Activations