© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5575
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to authority, particularly involving police or legal matters, that relate to people or organizations

    oai_token-act-pair · gemini-2.0-flash

    2015 current events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    tvguidetime
    -0.98
     Audiodateien
    -0.97
    曖昧さ回避
    -0.91
    Personendaten
    -0.91
    Билгалдахарш
    -0.90
     Paglinawan
    -0.89
    +#+#
    -0.88
    RenderAtEndOf
    -0.88
    rungsseite
    -0.86
     intptr
    -0.86
    POSITIVE LOGITS
     relevant
    0.45
    2
    0.42
    1
    0.39
    3
    0.39
    W
    0.38
     tri
    0.38
     all
    0.38
    w
    0.37
    relevant
    0.36
     sister
    0.36
    Activations Density 0.511%

    No Known Activations