© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1982
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in Russian related to online shopping and advertising

    oai_token-act-pair · gemini-2.0-flash

    mix of coding/languages

    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
    -0.89
     Houſe
    -0.81
     Monfieur
    -0.80
     Majefty
    -0.79
     tfsi
    -0.79
     PTS
    -0.78
     HN
    -0.77
     PMA
    -0.77
     TES
    -0.76
     Hec
    -0.75
    POSITIVE LOGITS
     rurale
    0.60
     littéraire
    0.52
     карьера
    0.50
     thèse
    0.48
     здание
    0.46
     tomba
    0.46
     cornea
    0.45
     abusos
    0.45
     акции
    0.45
     строительство
    0.45
    Activations Density 0.051%

    No Known Activations