© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2395
    Prev
    Next
    INDEX
    Explanations

    words in a Balkan language, possibly related to Facebook, mobile phones, and SMS messages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and data

    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
     Efq
    -0.60
    AccessorTable
    -0.60
     purpoſe
    -0.60
    ttino
    -0.57
     становника
    -0.56
     raiſ
    -0.55
     sī
    -0.54
     Monfieur
    -0.52
    HomeAsUpEnabled
    -0.52
     reaſon
    -0.51
    POSITIVE LOGITS
    rawDesc
    0.57
    dende
    0.48
    el
    0.48
    principalColumn
    0.46
    UnsafeEnabled
    0.46
    :].
    0.45
    :],
    0.45
     iprot
    0.44
     Saleh
    0.44
     Tuttle
    0.43
    Activations Density 0.866%

    No Known Activations