© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16143
    Prev
    Next
    INDEX
    Explanations

    java code that reads/writes files

    oai_token-act-pair · gemini-2.0-flash

    File input streams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    webElementGuid
    -0.74
     trajets
    -0.64
     محفوظة
    -0.61
    ographia
    -0.60
     AssemblyProduct
    -0.59
     Lid
    -0.58
    Lid
    -0.57
     <=",
    -0.57
     Cage
    -0.57
    łady
    -0.55
    POSITIVE LOGITS
    ORAGE
    0.49
     vPvB
    0.49
    كويكب
    0.44
     roux
    0.44
    ActivityCompat
    0.44
    #+#
    0.44
    Marshaller
    0.43
     Chwiliwch
    0.43
     lusso
    0.42
     indisponible
    0.41
    Activations Density 1.665%

    No Known Activations