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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14353
    Prev
    Next
    INDEX
    Explanations

    short words and fragments that come at the beginnings of phrases

    oai_token-act-pair · gemini-2.0-flash

    Business/legal texts

    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
    DockStyle
    -0.52
    of
    -0.52
    IBOutlet
    -0.52
     degeneracy
    -0.50
     Zivil
    -0.50
    ReusableCell
    -0.50
     diverge
    -0.49
    日閲覧
    -0.49
     úteis
    -0.48
    SourceChecksum
    -0.48
    POSITIVE LOGITS
     Fairly
    0.71
     fairly
    0.70
     الدولى
    0.55
     Comfor
    0.55
     Const
    0.53
     Buys
    0.52
     Well
    0.50
    Personendaten
    0.49
     
    0.49
    EndContext
    0.48
    Activations Density 9.329%

    No Known Activations