© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13606
    Prev
    Next
    INDEX
    Explanations

    periods and commas and possibly personal pronouns appearing at the end of clauses and sentences

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     invece
    -0.76
     dagegen
    -0.65
     OFDb
    -0.59
    EndContext
    -0.58
    ValueStyle
    -0.57
    通販
    -0.57
    Lähteet
    -0.53
     hingegen
    -0.52
    EDEFAULT
    -0.49
     kaarangay
    -0.49
    POSITIVE LOGITS
     Monfieur
    0.59
     الرياضيه
    0.59
    ſelf
    0.57
    ]._
    0.56
     ſtill
    0.54
    mingo
    0.53
    ſelves
    0.52
    anche
    0.52
    FontAwesome
    0.52
     fence
    0.51
    Activations Density 1.280%

    No Known Activations