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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1242
    Prev
    Next
    INDEX
    Explanations

    verbs related to negating or undoing something

    oai_token-act-pair · gemini-2.0-flash

    negate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     betweenstory
    -0.75
    Tembelea
    -0.69
    OGND
    -0.69
     mergeFrom
    -0.63
     myſelf
    -0.60
     itſelf
    -0.59
     snippetHide
    -0.57
    )))));
    -0.57
     ReSharper
    -0.57
    Datuak
    -0.56
    POSITIVE LOGITS
    pexpr
    0.52
    stdc
    0.51
    CppCodeGen
    0.50
    SequentialGroup
    0.49
     Prasad
    0.48
    /***/
    0.47
    แห่ง
    0.45
     post
    0.44
     Wer
    0.44
     situ
    0.44
    Activations Density 3.080%

    No Known Activations