© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    C code defining memory addresses and bitwise operations, likely for hardware interactions

    oai_token-act-pair · gemini-2.0-flash

    Code definitions

    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
     feroit
    -0.63
     enfans
    -0.60
     avoient
    -0.60
     auroit
    -0.56
     dieux
    -0.55
     étoit
    -0.53
     aikaa
    -0.53
     Grecs
    -0.53
     blessés
    -0.53
     Juifs
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.41
    Personendaten
    0.40
    obut
    0.40
     समीक्षाओं
    0.40
    ukone
    0.40
     INVOL
    0.40
     الاطلاع
    0.39
    ValueStyle
    0.39
     COND
    0.39
     DEL
    0.39
    Activations Density 14.959%

    No Known Activations