© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11489
    Prev
    Next
    INDEX
    Explanations

    the word "final" along with words that commonly occur around it.

    oai_token-act-pair · gemini-2.0-flash

    final

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     final
    -3.19
    final
    -3.03
    Final
    -2.92
     Final
    -2.86
     FINAL
    -2.66
    FINAL
    -2.63
     finalized
    -1.91
     finals
    -1.89
     finalize
    -1.84
     finalised
    -1.81
    POSITIVE LOGITS
    قایناقلار
    0.46
    MultipartFile
    0.44
    ist
    0.42
    WAU
    0.41
    isfile
    0.41
    ccccccc
    0.40
    ָה
    0.39
     f
    0.39
    Invalidate
    0.39
    bodyParser
    0.38
    Activations Density 1.637%

    No Known Activations