© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11091
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is expressing their opinion

    oai_token-act-pair · gemini-2.0-flash

    first-person statements indicating existence or identity

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

    am

    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
    chte
    -0.43
    monix
    -0.42
    бам
    -0.40
    paksa
    -0.39
     me
    -0.38
    cosx
    -0.38
     ven
    -0.38
    rentiel
    -0.38
     Run
    -0.38
    ]-'
    -0.38
    POSITIVE LOGITS
    SourceChecksum
    0.68
     StringTokenizer
    0.66
     disponibilités
    0.66
    الإنجليزية
    0.64
     &___
    0.63
     invokingState
    0.63
     Majefty
    0.63
     étoit
    0.62
     חיצוניים
    0.60
     Forumite
    0.60
    Activations Density 0.528%

    No Known Activations