© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16363
    Prev
    Next
    INDEX
    Explanations

    proper nouns and other capitalized words.

    oai_token-act-pair · gemini-2.0-flash

    Tully

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    +:+
    -0.98
    WriteTagHelper
    -0.93
    MigrationBuilder
    -0.89
     تضيفلها
    -0.88
     KGB
    -0.86
    onAttach
    -0.84
    例句
    -0.84
     dutch
    -0.82
    green
    -0.82
    OrNil
    -0.82
    POSITIVE LOGITS
    Información
    0.14
     AssemblyTitle
    0.14
     hindurch
    0.13
    )\}
    0.12
     körül
    0.11
    NUMX
    0.11
    )*/
    0.11
    ]**
    0.11
    ebaran
    0.10
    ssysteme
    0.10
    Activations Density 16.196%

    No Known Activations