© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8865
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings, accusations, and imprisonment

    oai_token-act-pair · gemini-2.0-flash

    legal charges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    شهاد
    -0.63
     --}}
    -0.59
    jooq
    -0.56
    owol
    -0.56
    )*/
    -0.56
     AssemblyVersion
    -0.56
     auffi
    -0.55
    })*/
    -0.55
     ***/
    -0.55
     /\.
    -0.55
    POSITIVE LOGITS
     charged
    0.50
    charged
    0.47
     accused
    0.46
    stateMutability
    0.46
    颊
    0.45
     disambiguazione
    0.44
     convicted
    0.44
     court
    0.44
    İstinadlar
    0.44
    uitton
    0.43
    Activations Density 30.838%

    No Known Activations