© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8253
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and places, especially those of Estonian origin, as well as abbreviations like "M."

    oai_token-act-pair · gemini-2.0-flash

    õ

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    parsedMessage
    -1.00
    UnsafeEnabled
    -0.82
    ResumeLayout
    -0.77
    Portail
    -0.71
    DebuggerNonUser
    -0.71
     Roskov
    -0.68
    contentLoaded
    -0.67
    Geplaatst
    -0.66
    بوابة
    -0.65
     kaarangay
    -0.64
    POSITIVE LOGITS
     sõ
    0.47
    kav
    0.43
     sélectionnez
    0.43
     négociations
    0.42
     verlassen
    0.41
    keta
    0.40
     prochaines
    0.40
     visites
    0.40
     progrès
    0.40
    anud
    0.40
    Activations Density 0.639%

    No Known Activations