© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4747
    Prev
    Next
    INDEX
    Explanations

    latex or other math and code formatting

    oai_token-act-pair · gemini-2.0-flash

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    RenderAtEndOf
    -0.84
     CreateTagHelper
    -0.73
    FormTagHelper
    -0.65
     فريبيس
    -0.63
     newBuilder
    -0.62
    المشاركات
    -0.57
    InputTagHelper
    -0.54
     Roskov
    -0.53
     motor
    -0.53
    DispatchToProps
    -0.52
    POSITIVE LOGITS
    AndEndTag
    0.65
    fjspx
    0.51
    )):
    0.49
    awaiter
    0.49
     continúas
    0.47
    labour
    0.46
    mybatisplus
    0.46
    #+#
    0.45
    CloseOperation
    0.45
     recognisable
    0.45
    Activations Density 2.344%

    No Known Activations