© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7235
    Prev
    Next
    INDEX
    Explanations

    the word "the" and adjectives describing large areas or nationalistic concepts .

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    Diwedd
    -0.64
    extField
    -0.55
    ########.
    -0.52
     digress
    -0.51
    źć
    -0.50
     compétence
    -0.50
     取
    -0.48
    InjectMocks
    -0.47
     poignée
    -0.47
    liciter
    -0.47
    POSITIVE LOGITS
     pinulongan
    0.58
    édrale
    0.55
    bootstrapcdn
    0.54
    IndentedString
    0.52
     muualla
    0.52
     ministry
    0.52
    FormTagHelper
    0.51
    encodeWith
    0.49
    AxisAlignment
    0.49
     Endlich
    0.49
    Activations Density 6.592%

    No Known Activations