© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15051
    Prev
    Next
    INDEX
    Explanations

    legal concepts related to crime, evidence, and punishment

    oai_token-act-pair · gemini-2.0-flash

    crimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     AssemblyCulture
    -0.59
     EconPapers
    -0.55
    UVWXYZ
    -0.54
    ">—
    -0.53
     Signalez
    -0.52
     समीक्षक
    -0.52
     GenerationType
    -0.50
     ویکی‌پدی
    -0.50
    +#+
    -0.49
    tiembre
    -0.49
    POSITIVE LOGITS
    NewUrlParser
    0.52
    SignedIn
    0.51
     russes
    0.49
     Româ
    0.48
     juries
    0.47
    ckså
    0.46
     Hanford
    0.46
     Zd
    0.45
    Havolalar
    0.45
    tragung
    0.45
    Activations Density 2.761%

    No Known Activations