© 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. 10315
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, people, and years in scientific publications, potentially including in-text citations

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     يتيمه
    -0.97
    GraphicsUnit
    -0.90
    DockStyle
    -0.85
     Normdatei
    -0.83
     InputDecoration
    -0.77
     wireType
    -0.76
    SequentialGroup
    -0.71
    +:+
    -0.71
    InjectAttribute
    -0.69
    /**
    -0.69
    POSITIVE LOGITS
    unehmen
    0.44
     renseignements
    0.44
    Genus
    0.43
     móds
    0.42
     PICTOGRAM
    0.41
    ERÍA
    0.40
     lisse
    0.40
    Alsace
    0.40
    ansch
    0.40
    Ữ
    0.40
    Activations Density 1.578%

    No Known Activations