© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2857
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude, agreement, concession, negative sentiment, or conversation about discussion and conflict.

    oai_token-act-pair · gemini-2.0-flash

    first-person pronouns

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

    first person singular

    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
     quæ
    -0.59
     greateſt
    -0.57
    Tikang
    -0.55
     EconPapers
    -0.55
    XmlAccessorType
    -0.53
    enderror
    -0.52
    ſelves
    -0.51
    OGND
    -0.51
     Momb
    -0.50
     noft
    -0.50
    POSITIVE LOGITS
     i
    2.56
    i
    1.49
     ive
    1.35
     im
    1.14
    僕の
    1.00
    僕が
    0.98
    僕も
    0.95
    僕
    0.92
     cant
    0.90
     dont
    0.90
    Activations Density 4.126%

    No Known Activations