© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12913
    Prev
    Next
    INDEX
    Explanations

    segments of personal, legal, or formal conversation

    oai_token-act-pair · gemini-2.0-flash

    continuations or qualifications in conversation

    np_token-act-pair-logits · gpt-4o-mini

    conversation transcript

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     الرياضيه
    -0.92
     Efq
    -0.88
     Majefty
    -0.84
     myſelf
    -0.80
     reaſon
    -0.78
     Monfieur
    -0.77
    ronpa
    -0.77
    脚注の使い方
    -0.77
     Jefus
    -0.75
     itſelf
    -0.74
    POSITIVE LOGITS
     (
    0.49
     Mark
    0.47
     that
    0.46
     L
    0.46
    mark
    0.45
     ()
    0.45
    ешься
    0.44
     посо
    0.44
    ITTLE
    0.44
    乾
    0.43
    Activations Density 3.097%

    No Known Activations