© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12820
    Prev
    Next
    INDEX
    Explanations

    words related to physical objects and surface orientation, especially in a technical setting

    oai_token-act-pair · gemini-2.0-flash

    orientation/position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ыгана
    -0.66
    éez
    -0.61
     BoxDecoration
    -0.60
    RenderAtEndOf
    -0.60
     TestBed
    -0.59
     OMIT
    -0.59
    NameInMap
    -0.59
    MigrationBuilder
    -0.58
     مكتب
    -0.56
    $/,
    -0.55
    POSITIVE LOGITS
     đáo
    0.57
     للاسماء
    0.54
    تقاوى
    0.47
     endwhile
    0.47
    InjectAttribute
    0.47
    ธิ
    0.46
    honneur
    0.46
     Bogen
    0.45
     Njema
    0.44
     בנושא
    0.43
    Activations Density 3.853%

    No Known Activations