© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8831
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of possibility or necessity

    oai_token-act-pair · gemini-2.0-flash

    Negative conditions

    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
    MENAFN
    -0.69
    edata
    -0.56
     Италијани
    -0.53
    ik
    -0.49
    erdings
    -0.47
    glor
    -0.47
    ed
    -0.46
    ibase
    -0.45
    AndEndTag
    -0.45
     glories
    -0.44
    POSITIVE LOGITS
    
    0.62
     disponibilités
    0.51
     attending
    0.51
    localctx
    0.49
     виправивши
    0.48
     clearing
    0.47
    migrationBuilder
    0.46
     introducido
    0.45
     Attending
    0.45
    uxley
    0.44
    Activations Density 8.012%

    No Known Activations