© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13116
    Prev
    Next
    INDEX
    Explanations

    words related to government processes and legal investigations, especially fraud

    oai_token-act-pair · gemini-2.0-flash

    corruption and illegal activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    DockStyle
    -0.71
    UnusedPrivate
    -0.68
     cherchés
    -0.63
    AndEndTag
    -0.62
     "..\..\
    -0.59
    +#+#
    -0.56
    Personendaten
    -0.56
    ngdoc
    -0.56
    LookAnd
    -0.55
     sanitarias
    -0.55
    POSITIVE LOGITS
     utafitiHapana
    0.54
    atzes
    0.50
     dipu
    0.48
     dusting
    0.48
    ritt
    0.47
    seeking
    0.46
    "%(
    0.45
    paigns
    0.45
    ustris
    0.44
    VISUAL
    0.44
    Activations Density 33.744%

    No Known Activations