© 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. 9196
    Prev
    Next
    INDEX
    Explanations

    text from social media posts, especially ones that involve personal feelings or experiences.

    oai_token-act-pair · gemini-2.0-flash

    variations of 'thank you' phrases

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

    gratitude/appreciation

    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
    PDOException
    -0.66
    CTYPE
    -0.57
    erapeu
    -0.56
    ”…
    -0.56
     nase
    -0.55
    ivably
    -0.55
     CURLOPT
    -0.54
    anstalt
    -0.54
    outchouc
    -0.53
     getM
    -0.53
    POSITIVE LOGITS
    Its
    0.65
     Its
    0.63
     its
    0.60
     Thanks
    0.59
    Thanks
    0.56
     THANKS
    0.53
    Pretty
    0.52
     Pretty
    0.52
     thanks
    0.51
     initComponents
    0.49
    Activations Density 2.881%

    No Known Activations