© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10196
    Prev
    Next
    INDEX
    Explanations

    code blocks with numbers/math and syntax characters

    oai_token-act-pair · gemini-2.0-flash

    Abbreviated words

    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
     démocr
    -0.73
     religieuses
    -0.64
     urbanas
    -0.64
     chré
    -0.63
     culturelles
    -0.59
     complètes
    -0.59
     sanitaires
    -0.57
     vérit
    -0.56
     avoient
    -0.56
     financières
    -0.56
    POSITIVE LOGITS
     rospy
    0.80
     LUT
    0.75
     LST
    0.75
     Parthen
    0.75
     WebDriverWait
    0.74
     crypt
    0.73
     CNT
    0.71
     Pyrene
    0.71
     POI
    0.70
     IAC
    0.69
    Activations Density 13.537%

    No Known Activations