© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6134
    Prev
    Next
    INDEX
    Explanations

    descriptive sentences about bad weather, especially winter

    oai_token-act-pair · gemini-2.0-flash

    snow and sand

    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
     ajutor
    -0.48
     elektri
    -0.46
     erk
    -0.46
    InputTagHelper
    -0.45
    יסטוריה
    -0.44
     JpaRepository
    -0.44
     ब्रेकडाउन
    -0.43
    Références
    -0.42
    Pages
    -0.42
     antidepress
    -0.42
    POSITIVE LOGITS
    ModelSerializer
    0.70
    LookAnd
    0.69
    MockMvc
    0.69
    IndentedString
    0.68
    phazard
    0.64
     snow
    0.63
    WebElementEntity
    0.62
    steamcommunity
    0.59
     noDo
    0.59
     EClass
    0.59
    Activations Density 0.679%

    No Known Activations