© 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. 11899
    Prev
    Next
    INDEX
    Explanations

    either a phrase starting with "filed a $" or the phrase "How we calculate these rates"

    oai_token-act-pair · gemini-2.0-flash

    Financial rates/lawsuits

    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
    AndEndTag
    -0.84
     CreateTagHelper
    -0.71
    ondissement
    -0.52
    DataItem
    -0.52
     capilla
    -0.50
     gratuitement
    -0.48
     fiscales
    -0.48
    lamydia
    -0.47
     ThemeData
    -0.47
    VIAF
    -0.47
    POSITIVE LOGITS
    migrationBuilder
    0.79
    //
    0.56
    /*
    0.53
    ">//
    0.53
    Personendaten
    0.52
    ]")]
    0.49
    onAttach
    0.49
    GGLE
    0.49
     ?>/
    0.46
    Datuak
    0.45
    Activations Density 0.249%

    No Known Activations