© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11321
    Prev
    Next
    INDEX
    Explanations

    the letters "Gi" followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    Gi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ly
    -1.05
    に
    -0.79
    了
    -0.77
    fully
    -0.71
    DockStyle
    -0.70
    mos
    -0.66
    theless
    -0.65
    mi
    -0.65
    men
    -0.63
    mente
    -0.63
    POSITIVE LOGITS
     encontraban
    0.32
    ارت
    0.31
     wata
    0.28
    한
    0.28
    O
    0.27
    A
    0.26
    ędzy
    0.26
    員の
    0.26
    Candidate
    0.25
    pplung
    0.25
    Activations Density 0.860%

    No Known Activations