© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11896
    Prev
    Next
    INDEX
    Explanations

    linguistic analysis of conversations

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     word
    -1.08
     words
    -0.95
    Word
    -0.92
    word
    -0.89
     vocabulary
    -0.89
     pronoun
    -0.89
     syllable
    -0.88
     nouns
    -0.87
     Word
    -0.86
    Words
    -0.85
    POSITIVE LOGITS
    VersionUID
    0.65
     newOwner
    0.54
    ponses
    0.51
    gsSP
    0.47
    Pratique
    0.44
    ภัณฑ์
    0.42
    ©
    0.42
    //});
    0.41
     chng
    0.41
    writeFieldEnd
    0.39
    Activations Density 0.504%

    No Known Activations