© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12808
    Prev
    Next
    INDEX
    Explanations

    the word "alignment" and words related to crystal displays

    oai_token-act-pair · gemini-2.0-flash

    alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     alignment
    -2.02
     aligned
    -1.92
     align
    -1.85
     Alignment
    -1.81
     Align
    -1.78
     aligning
    -1.75
     aligns
    -1.63
    Alignment
    -1.63
    alignment
    -1.60
     alignments
    -1.59
    POSITIVE LOGITS
    })`
    0.73
     autorytatywna
    0.70
    dafx
    0.65
    rungsseite
    0.63
     pinulongan
    0.57
     linkovi
    0.57
    bibinfo
    0.55
    ){$
    0.55
    mybatisplus
    0.54
    通販
    0.53
    Activations Density 2.872%

    No Known Activations