© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8645
    Prev
    Next
    INDEX
    Explanations

    French text, especially contractions starting with an apostrophe

    oai_token-act-pair · gemini-2.0-flash

    mixed-language chat

    np_max-act-logits · gemini-2.0-flash

    '

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     careful
    -0.82
     BoxDecoration
    -0.60
     Careful
    -0.57
    시오
    -0.56
    RotationOrder
    -0.54
     cautious
    -0.52
    Careful
    -0.51
     cab
    -0.50
    bourhood
    -0.50
     הזה
    -0.48
    POSITIVE LOGITS
    Билгалдахарш
    0.63
     nahilalakip
    0.59
    }".
    0.59
    getDeclared
    0.52
    assertIn
    0.50
     defaultstate
    0.50
     inſ
    0.50
    évaluateur
    0.50
     leſs
    0.49
    `).
    0.49
    Activations Density 0.300%

    No Known Activations