© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20269
    Prev
    Next
    INDEX
    Explanations

    Persian language context

    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_56_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
     Scene
    0.41
    ताज
    0.40
    moja
    0.39
     পর্বে
    0.39
    殯
    0.38
     fortunately
    0.38
     moja
    0.38
     Braxton
    0.38
     सहानुभूति
    0.37
     wcout
    0.36
    POSITIVE LOGITS
     po
    0.36
    imenti
    0.36
    нтип
    0.35
    ป์
    0.35
     skinny
    0.35
    poses
    0.34
     fires
    0.33
     mille
    0.33
    ﾁ
    0.33
     gav
    0.33
    Activations Density 0.003%

    No Known Activations