© 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-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4991
    Prev
    Next
    INDEX
    Explanations

    Greetings and different languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oh
    0.46
     proiz
    0.42
     testAvg
    0.41
    Oh
    0.40
     গুণ
    0.39
    iglie
    0.38
    entation
    0.38
    <0x83>
    0.38
     oras
    0.38
     shrimps
    0.38
    POSITIVE LOGITS
     Apoll
    0.40
    а
    0.39
    STA
    0.38
     Христо
    0.38
    REDIR
    0.37
    astly
    0.37
     содержимое
    0.36
    言って
    0.36
     H
    0.35
    upon
    0.35
    Activations Density 0.047%

    No Known Activations