© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9980
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and especially guilty pleas

    oai_token-act-pair · gemini-2.0-flash

    guilty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ebus
    -0.63
    cerely
    -0.57
    AIRE
    -0.55
    diat
    -0.54
     
    -0.54
    less
    -0.53
    EDE
    -0.52
    ming
    -0.52
    CEED
    -0.51
    sprung
    -0.51
    POSITIVE LOGITS
     ModelExpression
    1.21
    MigrationBuilder
    1.20
     pinulongan
    1.12
    TagMode
    1.08
     "..\..\..\
    1.02
     GenerationType
    1.02
    AndEndTag
    0.99
    +#+#
    0.96
    NameInMap
    0.96
    OGND
    0.96
    Activations Density 1.724%

    No Known Activations